AIRWiki - User contributions [en]

User:CarloDEramo

2016-03-01T13:54:38Z

CarloDEramo:

{{PhD
|category=PhD
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@polimi.it
|advisor=MarcelloRestelli
|resarea=Machine Learning
|photo=carloderamo.jpg
|status=active}}
Double MSc Degree in Computer Science at Politecnico di Milano and University of Illinois at Chicago (UIC) in 2015 with a Master Thesis on the use of Deep Boltzmann Machines (DBM) for road signs classification.
BSc Degree in Computer Science at Politecnico di Milano in 2011.

I'm currently a PhD student working on Deep Reinforcement Learning applied to financial trading.

User:CarloDEramo

2016-03-01T13:54:24Z

CarloDEramo:

{{PhD
|category=PhD
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@polimi.it
|advisor=MarcelloRestelli
resarea=Machine Learning
|photo=carloderamo.jpg
|status=active}}
Double MSc Degree in Computer Science at Politecnico di Milano and University of Illinois at Chicago (UIC) in 2015 with a Master Thesis on the use of Deep Boltzmann Machines (DBM) for road signs classification.
BSc Degree in Computer Science at Politecnico di Milano in 2011.

I'm currently a PhD student working on Deep Reinforcement Learning applied to financial trading.

User:CarloDEramo

2016-03-01T13:54:06Z

CarloDEramo:

{{PhD
|category=PhD
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@polimi.it
|advisor=MarcelloRestelli
resarea=MachineLearning
|photo=carloderamo.jpg
|status=active}}
Double MSc Degree in Computer Science at Politecnico di Milano and University of Illinois at Chicago (UIC) in 2015 with a Master Thesis on the use of Deep Boltzmann Machines (DBM) for road signs classification.
BSc Degree in Computer Science at Politecnico di Milano in 2011.

I'm currently a PhD student working on Deep Reinforcement Learning applied to financial trading.

User:CarloDEramo

2016-03-01T13:53:37Z

CarloDEramo:

{{PhD
|category=PhD
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@polimi.it
|advisor=Marcello Restelli
resarea=Machine Learning
|photo=carloderamo.jpg
|status=active}}
Double MSc Degree in Computer Science at Politecnico di Milano and University of Illinois at Chicago (UIC) in 2015 with a Master Thesis on the use of Deep Boltzmann Machines (DBM) for road signs classification.
BSc Degree in Computer Science at Politecnico di Milano in 2011.

I'm currently a PhD student working on Deep Reinforcement Learning applied to financial trading.

File:Carloderamo.jpg

2016-03-01T13:53:01Z

CarloDEramo:

User:CarloDEramo

2016-03-01T13:52:25Z

CarloDEramo:

{{PhD
|category=PhD
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@.polimi.it
|advisor=Marcello Restelli
resarea=Machine Learning
|photo=carloderamo.jpg
|status=active}}
Double MSc Degree in Computer Science at Politecnico di Milano and University of Illinois at Chicago (UIC) in 2015 with a Master Thesis on the use of Deep Boltzmann Machines (DBM) for road signs classification.
BSc Degree in Computer Science at Politecnico di Milano in 2011.

I'm currently a PhD student working on Deep Reinforcement Learning applied to financial trading.

User:CarloDEramo

2016-03-01T13:52:08Z

CarloDEramo:

{{PhD
|category=PhD
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@.polimi.it
|advisor=Marcello Restelli
resarea=Machine Learning
|photo=Foto.jpg
|status=active}}
Double MSc Degree in Computer Science at Politecnico di Milano and University of Illinois at Chicago (UIC) in 2015 with a Master Thesis on the use of Deep Boltzmann Machines (DBM) for road signs classification.
BSc Degree in Computer Science at Politecnico di Milano in 2011.

I'm currently a PhD student working on Deep Reinforcement Learning applied to financial trading.

User:CarloDEramo

2016-03-01T13:51:59Z

CarloDEramo:

{{PhD
|category=PhD
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@.polimi.it
|advisor=Marcello Restelli
resarea=Machine Learning
|photo=/home/shirokuma/Dropbox/Curriculum/Foto.jpg
|status=active}}
Double MSc Degree in Computer Science at Politecnico di Milano and University of Illinois at Chicago (UIC) in 2015 with a Master Thesis on the use of Deep Boltzmann Machines (DBM) for road signs classification.
BSc Degree in Computer Science at Politecnico di Milano in 2011.

I'm currently a PhD student working on Deep Reinforcement Learning applied to financial trading.

User:CarloDEramo

2016-03-01T13:50:28Z

CarloDEramo:

{{PhD
|category=PhD
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@.polimi.it
|advisor=Marcello Restelli
|photo=
|status=active}}
Double MSc Degree in Computer Science at Politecnico di Milano and University of Illinois at Chicago (UIC) in 2015 with a Master Thesis on the use of Deep Boltzmann Machines (DBM) for road signs classification.
BSc Degree in Computer Science at Politecnico di Milano in 2011.

I'm currently a PhD student working on Deep Reinforcement Learning applied to financial trading.

User:CarloDEramo

2016-03-01T13:49:27Z

CarloDEramo:

{{PhD
|category=PhD
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@.polimi.it
|advisor=[Marcello Restelli]
|photo=[[File:/home/shirokuma/Dropbox/Curriculum/Foto.JPG]]
|status=active}}
Double MSc Degree in Computer Science at Politecnico di Milano and University of Illinois at Chicago (UIC) in 2015 with a Master Thesis on the use of Deep Boltzmann Machines for road signs classification.
BSc Degree in Computer Science at Politecnico di Milano in 2011.

I'm currently a PhD studenti working on Deep Reinforcement Learning applied to financial trading.

User:CarloDEramo

2016-03-01T13:49:09Z

CarloDEramo:

{{PhD
|category=PhD
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@.polimi.it
|advisor=Marcello Restelli
|photo=[[File:/home/shirokuma/Dropbox/Curriculum/Foto.JPG]]
|status=active}}
Double MSc Degree in Computer Science at Politecnico di Milano and University of Illinois at Chicago (UIC) in 2015 with a Master Thesis on the use of Deep Boltzmann Machines for road signs classification.
BSc Degree in Computer Science at Politecnico di Milano in 2011.

I'm currently a PhD studenti working on Deep Reinforcement Learning applied to financial trading.

User:CarloDEramo

2016-03-01T13:48:30Z

CarloDEramo:

{{PhD Student
|category=PhD Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@.polimi.it
|advisor=Marcello Restelli
|photo=[[File:/home/shirokuma/Dropbox/Curriculum/Foto.JPG]]
|status=active}}
Double MSc Degree in Computer Science at Politecnico di Milano and University of Illinois at Chicago (UIC) in 2015 with a Master Thesis on the use of Deep Boltzmann Machines for road signs classification.
BSc Degree in Computer Science at Politecnico di Milano in 2011.

I'm currently a PhD studenti working on Deep Reinforcement Learning applied to financial trading.

User:CarloDEramo

2016-03-01T13:45:03Z

CarloDEramo:

{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|photo=[[File:/home/shirokuma/Dropbox/Curriculum/Foto.JPG]]
|status=active}}
I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.

During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep Boltzmann machines) for the [[Object Recognition with Deep Boltzmann Machines]] project.

User:CarloDEramo

2016-03-01T13:44:39Z

CarloDEramo:

{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|photo=/home/shirokuma/Dropbox/Curriculum/Foto.JPG
|status=active}}
I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.

During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep Boltzmann machines) for the [[Object Recognition with Deep Boltzmann Machines]] project.

User:CarloDEramo

2014-07-04T17:11:56Z

CarloDEramo:

{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|photo=[[Image:pic.jpg|200px|thumb|center]]
|status=active}}
I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.

During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep Boltzmann machines) for the [[Object Recognition with Deep Boltzmann Machines]] project.

User:CarloDEramo

2014-07-04T17:10:58Z

CarloDEramo:

{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|photo=[[Image:pic.jpg|200px|thumb|center]]
|status=active}}
I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.

During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

Object Recognition with Deep Boltzmann Machines

2014-07-02T22:41:19Z

CarloDEramo: /* Intro */

== Intro ==
This project aims to exploit the ability of Deep Boltzmann machines (DBM) to classify (and generate) multiclass objects. Initially, they will be used to classify road signs with the purpose to help the navigation of an hypotetical autonomous car. Since the initial results on the classification tasks of road signs using DBM are very good, we are pretty confident about the quality of the project. After that, we will consider the possibility to extend the task to other domains.{{Project | title=Object recognition with DBMs | short_descr= Deep Boltzmann machines for classification tasks | coordinator=MatteoMatteucci | tutor=MatteoMatteucci;FrancescoVisin | students=CarloDEramo | resarea=Robotics | restopic=Machine Learning | start=2014/03/1 | level=Ms | status=Active}}

== Deep learning and Boltzmann machines ==
'''Deep learning''' is a set of algorithms in machine learning that attempt to model high-level abstractions in data by using architectures composed of multiple non-linear transformations.
We will work on Boltzmann machines, an energy-based model which has been proven to perform very well in image and speech recognition tasks. A Boltzmann machines is composed of visible units representing the inputs of the network provided by the dataset and hidden units representing the feature detectors of the net. In a general fully connected Boltzmann machine each pair of unit is connected with a symmetric connection with a certain weights. We will focus on DBMs that are a particular type of Boltzmann machines built by stacking several layers of RBM on top of each other in a proper way. A RBM is known as restricted Boltzmann machines, a Boltzmann machines with no intra-layer connections. We'll study also deep belief network (DBN), a hybrid model between a neural network with discriminative and generative connections and a DBM, which has only symmetric connections.
We will use ''Pylearn2'' framework which offers training procedures of deep neural networks. During the project we will go deep in the analysis of this kind of networks studying their potentiality and flexibility; we'll try different configuration of networks in order to obtain the good performances we're looking for.

Object Recognition with Deep Boltzmann Machines

2014-07-02T22:40:59Z

CarloDEramo: /* Intro */

== Intro ==
This project aims to exploit the ability of Deep Boltzmann machines (DBM) to classify (and generate) multiclass objects. Initially, they will be used to classify road signs with the purpose to help the navigation of an hypotetical autonomous car. Since the initial results on the classification tasks of road signs using DBM are very good, we are pretty confident about the quality of the project. After that, we will consider the possibility to extend the task to other domains.{{Project | title=Object recognition with DBM | short_descr= Boltzmann machines for classification tasks | coordinator=MatteoMatteucci | tutor=MatteoMatteucci;FrancescoVisin | students=CarloDEramo | resarea=Robotics | restopic=Machine Learning | start=2014/03/1 | level=Ms | status=Active}}

== Deep learning and Boltzmann machines ==
'''Deep learning''' is a set of algorithms in machine learning that attempt to model high-level abstractions in data by using architectures composed of multiple non-linear transformations.
We will work on Boltzmann machines, an energy-based model which has been proven to perform very well in image and speech recognition tasks. A Boltzmann machines is composed of visible units representing the inputs of the network provided by the dataset and hidden units representing the feature detectors of the net. In a general fully connected Boltzmann machine each pair of unit is connected with a symmetric connection with a certain weights. We will focus on DBMs that are a particular type of Boltzmann machines built by stacking several layers of RBM on top of each other in a proper way. A RBM is known as restricted Boltzmann machines, a Boltzmann machines with no intra-layer connections. We'll study also deep belief network (DBN), a hybrid model between a neural network with discriminative and generative connections and a DBM, which has only symmetric connections.
We will use ''Pylearn2'' framework which offers training procedures of deep neural networks. During the project we will go deep in the analysis of this kind of networks studying their potentiality and flexibility; we'll try different configuration of networks in order to obtain the good performances we're looking for.

Object Recognition with Deep Boltzmann Machines

2014-07-02T22:38:08Z

CarloDEramo: /* Intro */

== Intro ==
This project aims to exploit the ability of Deep Boltzmann machines (DBM) to classify (and generate) multiclass objects. Initially, they will be used to classify road signs with the purpose to help the navigation of an hypotetical autonomous car. Since the initial results on the classification tasks of road signs using DBM are very good, we are pretty confident about the quality of the project. After that, we will consider the possibility to extend the task to other domains.{{Project | title=Boltzmann machines | short_descr= Boltzmann machines for classification tasks | coordinator=MatteoMatteucci | tutor=MatteoMatteucci;FrancescoVisin | students=CarloDEramo | resarea=Robotics | restopic=Machine Learning | start=2014/03/1 | level=Ms | status=Active}}

== Deep learning and Boltzmann machines ==
'''Deep learning''' is a set of algorithms in machine learning that attempt to model high-level abstractions in data by using architectures composed of multiple non-linear transformations.
We will work on Boltzmann machines, an energy-based model which has been proven to perform very well in image and speech recognition tasks. A Boltzmann machines is composed of visible units representing the inputs of the network provided by the dataset and hidden units representing the feature detectors of the net. In a general fully connected Boltzmann machine each pair of unit is connected with a symmetric connection with a certain weights. We will focus on DBMs that are a particular type of Boltzmann machines built by stacking several layers of RBM on top of each other in a proper way. A RBM is known as restricted Boltzmann machines, a Boltzmann machines with no intra-layer connections. We'll study also deep belief network (DBN), a hybrid model between a neural network with discriminative and generative connections and a DBM, which has only symmetric connections.
We will use ''Pylearn2'' framework which offers training procedures of deep neural networks. During the project we will go deep in the analysis of this kind of networks studying their potentiality and flexibility; we'll try different configuration of networks in order to obtain the good performances we're looking for.

Object Recognition with Deep Boltzmann Machines

2014-07-02T22:37:36Z

CarloDEramo: /* Deep learning and Boltzmann machines */

== Intro ==
This project aims to exploit the ability of Deep Belief Network (DBN) to classify (and generate) multiclass objects. Initially, they will be used to classify road signs with the purpose to help the navigation of an hypotetical autonomous car. Since the initial results on the classification tasks of road signs using DBN are very good, we are pretty confident about the quality of the project. After that, we will consider the possibility to extend the task to other domains.{{Project | title=Boltzmann machines | short_descr= Boltzmann machines for classification tasks | coordinator=MatteoMatteucci | tutor=MatteoMatteucci;FrancescoVisin | students=CarloDEramo | resarea=Robotics | restopic=Machine Learning | start=2014/03/1 | level=Ms | status=Active}}

== Deep learning and Boltzmann machines ==
'''Deep learning''' is a set of algorithms in machine learning that attempt to model high-level abstractions in data by using architectures composed of multiple non-linear transformations.
We will work on Boltzmann machines, an energy-based model which has been proven to perform very well in image and speech recognition tasks. A Boltzmann machines is composed of visible units representing the inputs of the network provided by the dataset and hidden units representing the feature detectors of the net. In a general fully connected Boltzmann machine each pair of unit is connected with a symmetric connection with a certain weights. We will focus on DBMs that are a particular type of Boltzmann machines built by stacking several layers of RBM on top of each other in a proper way. A RBM is known as restricted Boltzmann machines, a Boltzmann machines with no intra-layer connections. We'll study also deep belief network (DBN), a hybrid model between a neural network with discriminative and generative connections and a DBM, which has only symmetric connections.
We will use ''Pylearn2'' framework which offers training procedures of deep neural networks. During the project we will go deep in the analysis of this kind of networks studying their potentiality and flexibility; we'll try different configuration of networks in order to obtain the good performances we're looking for.

Object Recognition with Deep Boltzmann Machines

2014-07-02T22:37:01Z

CarloDEramo:

== Intro ==
This project aims to exploit the ability of Deep Belief Network (DBN) to classify (and generate) multiclass objects. Initially, they will be used to classify road signs with the purpose to help the navigation of an hypotetical autonomous car. Since the initial results on the classification tasks of road signs using DBN are very good, we are pretty confident about the quality of the project. After that, we will consider the possibility to extend the task to other domains.{{Project | title=Boltzmann machines | short_descr= Boltzmann machines for classification tasks | coordinator=MatteoMatteucci | tutor=MatteoMatteucci;FrancescoVisin | students=CarloDEramo | resarea=Robotics | restopic=Machine Learning | start=2014/03/1 | level=Ms | status=Active}}

== Deep learning and Deep Belief Network ==
'''Deep learning''' is a set of algorithms in machine learning that attempt to model high-level abstractions in data by using architectures composed of multiple non-linear transformations.
We will work on Boltzmann machines, an energy-based model which has been proven to perform very well in image and speech recognition tasks. A Boltzmann machines is composed of visible units representing the inputs of the network provided by the dataset and hidden units representing the feature detectors of the net. In a general fully connected Boltzmann machine each pair of unit is connected with a symmetric connection with a certain weights. We will focus on DBMs that are a particular type of Boltzmann machines built by stacking several layers of RBM on top of each other in a proper way. A RBM is known as restricted Boltzmann machines, a Boltzmann machines with no intra-layer connections. We'll study also deep belief network (DBN), a hybrid model between a neural network with discriminative and generative connections and a DBM, which has only symmetric connections.
We will use ''Pylearn2'' framework which offers training procedures of deep neural networks. During the project we will go deep in the analysis of this kind of networks studying their potentiality and flexibility; we'll try different configuration of networks in order to obtain the good performances we're looking for.

Object Recognition with Deep Boltzmann Machines

2014-07-02T22:35:25Z

CarloDEramo: /* Deep learning and Deep Belief Network */

== Intro ==
This project aims to exploit the ability of Deep Belief Network (DBN) to classify (and generate) multiclass objects. Initially, they will be used to classify road signs with the purpose to help the navigation of an hypotetical autonomous car. Since the initial results on the classification tasks of road signs using DBN are very good, we are pretty confident about the quality of the project. After that, we will consider the possibility to extend the task to other domains.{{Project | title=DBN | short_descr= DBN for classification tasks | coordinator=MatteoMatteucci | tutor=MatteoMatteucci;FrancescoVisin | students=CarloDEramo | resarea=Robotics | restopic=Machine Learning | start=2014/03/1 | level=Ms | status=Active}}

== Deep learning and Deep Belief Network ==
'''Deep learning''' is a set of algorithms in machine learning that attempt to model high-level abstractions in data by using architectures composed of multiple non-linear transformations.
We will work on Boltzmann machines, an energy-based model which has been proven to perform very well in image and speech recognition tasks. A Boltzmann machines is composed of visible units representing the inputs of the network provided by the dataset and hidden units representing the feature detectors of the net. In a general fully connected Boltzmann machine each pair of unit is connected with a symmetric connection with a certain weights. We will focus on DBMs that are a particular type of Boltzmann machines built by stacking several layers of RBM on top of each other in a proper way. A RBM is known as restricted Boltzmann machines, a Boltzmann machines with no intra-layer connections. We'll study also deep belief network (DBN), a hybrid model between a neural network with discriminative and generative connections and a DBM, which has only symmetric connections.
We will use ''Pylearn2'' framework which offers training procedures of deep neural networks. During the project we will go deep in the analysis of this kind of networks studying their potentiality and flexibility; we'll try different configuration of networks in order to obtain the good performances we're looking for.

User:CarloDEramo

2014-02-28T14:10:24Z

CarloDEramo:

{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=[[Image:pic.jpg|200px|thumb|center]]
|status=active}}
I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.

During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

User:CarloDEramo

2014-02-28T14:08:31Z

CarloDEramo:

{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=[[Image:pic.jpg|thumb|center]]
|status=active}}
I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.

During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

User:CarloDEramo

2014-02-28T14:06:34Z

CarloDEramo:

{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=[[File:pic.jpg|thumb|center]]
|status=active}}
I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.

During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

User:CarloDEramo

2014-02-28T14:06:18Z

CarloDEramo:

{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=[[File:pic.jpg|center]]
|status=active}}
I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.

During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

User:CarloDEramo

2014-02-28T14:05:58Z

CarloDEramo:

{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=[[File:pic.jpg|thumb|center]]
|status=active}}
I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.

During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

User:CarloDEramo

2014-02-28T14:05:38Z

CarloDEramo:

{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=[[File:pic.jpg|200px|thumb|center]]
|status=active}}
I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.

During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

User:CarloDEramo

2014-02-28T14:04:24Z

CarloDEramo:

{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=[[File:pic.jpg|200px|thumb|center|alt text]]
|status=active}}
I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.

During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

User:CarloDEramo

2014-02-28T14:03:58Z

CarloDEramo:

{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=[[File:pic.jpg|200px|thumb|left|alt text]]
|status=active}}
I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.

During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

User:CarloDEramo

2014-02-28T14:03:37Z

CarloDEramo:

I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.
{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=[[File:pic.jpg|200px|thumb|left|alt text]]
|status=active}}
During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

User:CarloDEramo

2014-02-28T14:03:28Z

CarloDEramo:

I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.
{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=[[File:pi.jpg|200px|thumb|left|alt text]]
|status=active}}
During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

User:CarloDEramo

2014-02-28T14:00:37Z

CarloDEramo:

I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.
{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=[[File:pi.jpg]]
|status=active}}
During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

User:CarloDEramo

2014-02-28T14:00:10Z

CarloDEramo:

I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.
{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=[[File:pic.jpg]]
|status=active}}
During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

File:Pic.jpg

2014-02-28T13:59:40Z

CarloDEramo:

User:CarloDEramo

2014-02-28T13:59:00Z

CarloDEramo:

I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.
{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=[[File:IMG_20140228_102810.jpg]]
|status=active}}
During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

User:CarloDEramo

2014-02-28T13:58:05Z

CarloDEramo:

I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011.
{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=
|status=active}}
During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.

User:CarloDEramo

2014-02-28T13:57:34Z

CarloDEramo:

I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011. During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the [[Object Recognition with Deep Belief Networks]] project.
{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=
|status=active}}

User:CarloDEramo

2014-02-28T13:57:08Z

CarloDEramo:

I'm a M.Sc. student of computer science, working on my thesis. I was born on 26th march 1989 in Pescara. I studied at Liceo Scientifico and got my high school diploma in 2008. Afterwards, I got my bachelor degree in computer science at Politecnico Di Milano in 2011. During my academic years I found myself very interested in artificial intelligence and robotics topics and that's why I've chosen a thesis about these stuff. Moreover, I like all subjects dealing with math and physics too. I'm currently working on neural networks (more precisely, deep belief networks) for the ''[[Object Recognition with Deep Belief Networks]]'' project.
{{Student
|category=Student
|firstname=Carlo
|lastname=D'Eramo
|email=carlo.deramo@mail.polimi.it
|advisor=MatteoMatteucci
|projectpage=Object_Recognition_with_Deep_Belief_Networks
|photo=
|status=active}}

Object Recognition with Deep Boltzmann Machines

2014-02-27T23:33:01Z

CarloDEramo: /* Intro */

== Intro ==
This project aims to exploit the ability of Deep Belief Network (DBN) to classify (and generate) multiclass objects. Initially, they will be used to classify road signs with the purpose help the navigation of an hypotetical autonomous car. Since the initial results on the classification tasks of road signs using DBN are very good, we are pretty confident about the quality of the project. After that, we will consider the possibility to extend the task to other domains.{{Project | title=DBN | short_descr= DBN for classification tasks | coordinator=MatteoMatteucci | tutor=MatteoMatteucci;FrancescoVisin | students=CarloDEramo | resarea=Robotics | restopic=Machine Learning | start=2014/03/1 | level=Ms | status=Active}}

== Deep learning and Deep Belief Network ==
'''Deep learning''' is a set of algorithms in machine learning that attempt to model high-level abstractions in data by using architectures composed of multiple non-linear transformations.
A '''deep belief network''' (DBN) is used for deep learning tasks, it is a generative graphical model, or alternatively a type of deep neural network, composed of multiple layers of latent variables ("hidden units"), with connections between the layers but not between units within each layer. More precisely, each layer acts as a ''feature detector'' on inputs and serves as the visible layer for the next. In this way it is possible to have a fast unsupervised training procedure which will be very useful for the purpose of our project due to the complexity of the domain.
We will use ''Pylearn2'' framework which offers training procedures of deep neural networks. During the project we will go deep in the analysis of this kind of network studying their potentiality and flexibility; we'll try different configuration of network in order to obtain the good performances we're looking for.

Object Recognition with Deep Boltzmann Machines

2014-02-27T23:21:04Z

CarloDEramo: /* Deep learning and Deep Belief Network */

== Intro ==
This project aims to exploit the ability of Deep Belief Network (DBN) to classify (and generate) multiclass objects. Initially, they will be used to classify road signs with the purpose help the navigation of an hypotetical autonomous car. Since the initial results on the classification tasks of road signs using DBN are very good, we are pretty confident about the quality of the project.{{Project | title=DBN | short_descr= DBN for classification tasks | coordinator=MatteoMatteucci | tutor=MatteoMatteucci;FrancescoVisin | students=CarloDEramo | resarea=Robotics | restopic=Machine Learning | start=2014/03/1 | level=Ms | status=Active}}

== Deep learning and Deep Belief Network ==
'''Deep learning''' is a set of algorithms in machine learning that attempt to model high-level abstractions in data by using architectures composed of multiple non-linear transformations.
A '''deep belief network''' (DBN) is used for deep learning tasks, it is a generative graphical model, or alternatively a type of deep neural network, composed of multiple layers of latent variables ("hidden units"), with connections between the layers but not between units within each layer. More precisely, each layer acts as a ''feature detector'' on inputs and serves as the visible layer for the next. In this way it is possible to have a fast unsupervised training procedure which will be very useful for the purpose of our project due to the complexity of the domain.
We will use ''Pylearn2'' framework which offers training procedures of deep neural networks. During the project we will go deep in the analysis of this kind of network studying their potentiality and flexibility; we'll try different configuration of network in order to obtain the good performances we're looking for.

Object Recognition with Deep Boltzmann Machines

2014-02-27T22:59:42Z

CarloDEramo: /* Deep Belief Network */

Object Recognition with Deep Boltzmann Machines

2014-02-27T22:45:31Z

CarloDEramo:

Object Recognition with Deep Boltzmann Machines

2014-02-27T22:41:28Z

CarloDEramo:

Object Recognition with Deep Boltzmann Machines

2014-02-27T22:41:13Z

CarloDEramo:

Object Recognition with Deep Boltzmann Machines

2014-02-27T22:40:58Z

CarloDEramo:

This project aims to exploit the ability of Deep Belief Network (DBN) to classify (and generate) multiclass objects. Initially, they will be used to classify road signs with the purpose help the navigation of an hypotetical autonomous car. Since the initial results on the classification tasks of road signs using DBN are very good, we are pretty confident about the quality of the project.{{Project | title=DBN | short_descr= DBN for classification tasks | coordinator=MatteoMatteucci | tutor=MatteoMatteucci;FrancescoVisin | students=CarloDEramo | resarea=Robotics | restopic=Machine Learning | start=2014/03/1 | level=Ms | status=Active}}

== fda ==

Object Recognition with Deep Boltzmann Machines

2014-02-27T22:40:12Z

CarloDEramo:

Object Recognition with Deep Boltzmann Machines

2014-02-27T22:26:41Z

CarloDEramo:

asSs{{Project | title=DBN | short_descr= DBN for classification tasks | coordinator=MatteoMatteucci | tutor=MatteoMatteucci;FrancescoVisin | students=CarloDEramo | resarea=Robotics | restopic=Machine Learning | start=2014/03/1 | level=Ms | status=Active}}

Object Recognition with Deep Boltzmann Machines

2014-02-27T22:26:27Z

CarloDEramo:

asSs{{Prova | title=DBN | short_descr= DBN for classification tasks | coordinator=MatteoMatteucci | tutor=MatteoMatteucci;FrancescoVisin | students=CarloDEramo | resarea=Robotics | restopic=Machine Learning | start=2014/03/1 | level=Ms | status=Active}}

Object Recognition with Deep Boltzmann Machines

2014-02-27T22:26:08Z

CarloDEramo:

asSs{{Project=prova | title=DBN | short_descr= DBN for classification tasks | coordinator=MatteoMatteucci | tutor=MatteoMatteucci;FrancescoVisin | students=CarloDEramo | resarea=Robotics | restopic=Machine Learning | start=2014/03/1 | level=Ms | status=Active}}