KitKat:
giovedì 25 febbraio 2016
mercoledì 17 febbraio 2016
Homework #6 - Taxonomy of a Machine
Machine Learning Algorithms
| Paradigm | Learning rule | Architecture | Learning algorithm | Task |
| Supervised | Error-correction | Single or multilayer perceptron | Perceptron rule, Stochastic gradient descent, Back propagation, BP+reinf, SBPI | Pattern Classification, Functions Approximation, Prediction, Control |
| Convolutional Networks | Stochastic gradient descent, Back propagation | Classification, Computer Vision, Speech recognition | ||
| Auto-encoders | Gradient Descent | Data compression, Preprocessing | ||
| Competitive | Competitive | Learning Vector Quantization | Within Class Categorization, Data Compression | |
| Unsupervised | Hebbian | Recurrent | Hebb rule | Denoising, Attractor Learning |
| Hopfield Network | Hebb rule, Inference (BP, TAP, Montecarlo) | Memory, Denoising, Attractor Learning | ||
| Boltzmann | Boltzamann Machine | Contrastive divergence, Statistical Inference | Feature Learning, Preprocessing, Denoising, Generative model | |
| Kohonen's SOM | Kohonen's SOM | Kohonen's SOM | Data Analysis |
Supervised VS Unsupervised
Data can be labeled or not
martedì 16 febbraio 2016
Homework #5 - Logos&Machines
Valve Software, an American video game developer and digital distribution company headquartered in Bellevue, Washington (US), founded in 1996.
Bad Robot Productions (known as only Bad Robot when first founded in 2001) is an American film and television production company owned by J. J. Abrams.
Bad Robot Productions (known as only Bad Robot when first founded in 2001) is an American film and television production company owned by J. J. Abrams.
Homework #4 - Words&Machines
Perceptron -- a perceiving and recognizing self-operating machine (F. Rosenblatt, 1957).
Adaline -- Adaptive Linear Neuron, is an early single-layer artificial neural network using memistors. Developed by Professor Bernard Widrow in 1960, it is based on the McCulloch–Pitts neuron. It consists of a weight, a bias and a summation function.
Memristor -- portmanteau of memory resistor, is a non-linear passive two-terminal electrical component relating electric charge and magnetic flux linkage. The memristor's present electrical resistance depends on how much electric charge has flowed in what direction through it in the past. The device remembers its history—the so-called non-volatility property. When the electric power supply is turned off, the memristor remembers its most recent resistance until it is turned on again.
Adaline -- Adaptive Linear Neuron, is an early single-layer artificial neural network using memistors. Developed by Professor Bernard Widrow in 1960, it is based on the McCulloch–Pitts neuron. It consists of a weight, a bias and a summation function.
Memristor -- portmanteau of memory resistor, is a non-linear passive two-terminal electrical component relating electric charge and magnetic flux linkage. The memristor's present electrical resistance depends on how much electric charge has flowed in what direction through it in the past. The device remembers its history—the so-called non-volatility property. When the electric power supply is turned off, the memristor remembers its most recent resistance until it is turned on again.
Homework #3 - The Machine of my Doctorate
Artificial neural networks
Inspired strongly from the visual system, the Multi-layer Perceptron is a device capable of performing a classification task, learning from set of input-output associations often called training set. The presence of many layers of interconnected artificial neurons allows for a sequential processing of the raw data in input, and for the representation of arbitrarily complex non-linear functions of it. The parameters of the device are usually referred to as synaptic weights: these are able to capture complex structures (features) in the inputs, which, after the training is complete, can be used to obtain a correct classification when an unseen pattern is presented. This mechanism is likely very similar to the learning process taking place in the brain.
Inspired strongly from the visual system, the Multi-layer Perceptron is a device capable of performing a classification task, learning from set of input-output associations often called training set. The presence of many layers of interconnected artificial neurons allows for a sequential processing of the raw data in input, and for the representation of arbitrarily complex non-linear functions of it. The parameters of the device are usually referred to as synaptic weights: these are able to capture complex structures (features) in the inputs, which, after the training is complete, can be used to obtain a correct classification when an unseen pattern is presented. This mechanism is likely very similar to the learning process taking place in the brain.
My research activity
I am currently attending the second year of my doctoral degree in Physics.
The main aim of my PhD studies is to contribute to the development of a statistical mechanical description of learning, both in biological and artificial neural networks.
Mimicking the brain efficiency in representing the world surrounding us can be very fruitful from an engineering perspective, but is certainly also very instructive when one looks to identify the requirements of the learning mechanisms and memory.
The main aim of my PhD studies is to contribute to the development of a statistical mechanical description of learning, both in biological and artificial neural networks.
Mimicking the brain efficiency in representing the world surrounding us can be very fruitful from an engineering perspective, but is certainly also very instructive when one looks to identify the requirements of the learning mechanisms and memory.
Homework #2 - Comics&Machines
"Machine Célibataires" in the comics:
In 1931 the Merriam-Webster dictionary adopted the phrase "Rube Goldberg" as an adjective defined as accomplishing something simple through complicated means:
In 1931 the Merriam-Webster dictionary adopted the phrase "Rube Goldberg" as an adjective defined as accomplishing something simple through complicated means:
Self-operating Napkin, by Rude Goldberg
Homework #1 - Music&Machines
"The Bolt", Shostakovich
Right after composing the celebrated satirical opera "The Nose", between 1930 and 1931 Dmitri Shostakovich puts to music an ironic tale of slovenly work in a Soviet factory. The lazy Lyonka hates work and together with a local priest and anti-Soviet plotter he plans to sabotage the machinery by putting a bolt in it. Their plan is obviously destined to failure, put to an end by a group of Young Communists.
Right after composing the celebrated satirical opera "The Nose", between 1930 and 1931 Dmitri Shostakovich puts to music an ironic tale of slovenly work in a Soviet factory. The lazy Lyonka hates work and together with a local priest and anti-Soviet plotter he plans to sabotage the machinery by putting a bolt in it. Their plan is obviously destined to failure, put to an end by a group of Young Communists.
Homework #0 - The Book
When the individual gears play an obscure role in the even obscurer purpose of the machine as a whole..
I will analyse how the dystopia-like "machinery of justice" presented in "The Trial" by Franz Kafka, swallows up the life of Josef K., an helpless chief financial officer of a German bank. For no apparent reason.
"The Trial", Pink Floyd ("The Wall", 1979)
I will analyse how the dystopia-like "machinery of justice" presented in "The Trial" by Franz Kafka, swallows up the life of Josef K., an helpless chief financial officer of a German bank. For no apparent reason.
"The Trial", Pink Floyd ("The Wall", 1979)
Iscriviti a:
Post (Atom)