Deep Learning Autoencoder Models

Deep Learning ? Autoencoder Models

Davide Bacciu

Dipartimento di Informatica Universit? di Pisa

Intelligent Systems for Pattern Recognition (ISPR)

Introduction Deep Autoencoder

Applications

Generative Models Wrap-up Deep Learning Module Lecture

Generative Graphical Models

Bayesian Models/Nets

z

w

N

K

M

? Unsupervised data understanding

? Interpretability ? Weak on supervised

performance

Markov Random Fields

Yi

Yj

Xi

? Knowledge and constraints through feature functions

? CRF: the supervised way to generative

? Computationally heavy

Dynamic Models

t S21

Q12 S22

Q22 S23

Y2

? Topology unfolds on data structure

? Structured data processing

? Complex causal relationships

Introduction Deep Autoencoder

Applications

Generative Models Wrap-up Deep Learning Module Lecture

Module's Take Home Messages

? Consider using generative models when

? Need interpretability ? Need to incorporate prior knowledge ? Unsupervised learning or learning with partially observable

supervision ? Need reusable/portable learned knowledge

? Consider avoiding generative models when

? Having tight computational constraints ? Dealing with raw, noisy low level data

? Variational inference

? Efficient way to learn an approximation to intractable distributions

? The variational function can be a neural network

Introduction Deep Autoencoder

Applications

Deep Learning

Generative Models Wrap-up Deep Learning Module Lecture

AI

Prediction

Hard-coded expert

reasoning

Trainable predictor

Expertdesigned features

Learned features

ANN

ML

Input

Deep Learning

Learned feature hierarchy

Introduction Deep Autoencoder

Applications

Module Outline

Generative Models Wrap-up Deep Learning Module Lecture

? Recurrent, recursive and contextual (Micheli)

? Recurrent NN training refresher ? Recursive NN ? Graph processing

? Foundational models

? Deep Autoencoders and RBM ? Convolutional Neural Networks ? Gated Recurrent Networks (LSTM, ...)

? Advanced topics

? Adversarial models, memory networks and attentional models ? Variational deep learning ? Deep reinforcement learning

API and applications seminars

 ................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download