NOC:Deep Learning - Part 2 - Study24x7
Social learning Network
NOC:Deep Learning - Part 2
broucher Course Brochure
NOC:Deep Learning - Part 2
by Prof Mitesh Khapra

Deep learning (also known as deep structured learning or hierarchical learning) is part of a broader family of machine learning methods based on artificial neural networks. Learning can be supervised, semi-supervised or unsupervised.Deep learning architectures such as deep neural networks, deep belief networks, recurrent neural networks and convolu...

0.0  (0 Ratings) 1091 Learner
validy img Validity Unlimited
level All Level
level English
cover Img Preview not available
Program Fee
FREE
About This Course

Deep learning (also known as deep structured learning or hierarchical learning) is part of a broader family of machine learning methods based on artificial neural networks. Learning can be supervised, semi-supervised or unsupervised.Deep learning architectures such as deep neural networks, deep belief networks, recurrent neural networks and convolu...

Show more
Course Curriculum
8 Sections | 37 Lecture | 10h 03min total length
Expand all sections
NOC:Deep Learning - Part 2

WEEK 1

| 01h 15min total length
  • <?php echo $alt; ?>

    Recap of Probability Theory

    15m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Why are we interested in Joint Distributions

    6m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    How do we represent a joint distribution

    4m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Can we represent the joint distribution more compactly

    15m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Can we use a graph to represent a joint distribution

    17m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Different types of reasoning encoded in a Bayesian Network

    16m <?php echo $alt; ?>
NOC:Deep Learning - Part 2

Week 2

| 01h 25min total length
  • <?php echo $alt; ?>

    Independencies encoded by a Bayesian Network(Case 1: Node and it's parents)

    6m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Independencies encoded by a Bayesian Network

    5m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Independencies encoded by a Bayesian Network

    3m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Bayesian Networks : Formal Semantics

    3m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    I-Maps

    12m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Markov Networks: Motivation

    16m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Factors in Markov Network

    21m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Local Independencies in a Markov Network

    15m <?php echo $alt; ?>
NOC:Deep Learning - Part 2

Week 3

| 01h 55min total length
  • <?php echo $alt; ?>

    Joint Distributions

    27m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    The concept of a latent variable

    27m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Restricted Boltzmann Machines

    30m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    RBMs as Stochastic Neural Networks

    14m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Unsupervised Learning with RBMs

    14m <?php echo $alt; ?>
NOC:Deep Learning - Part 2

Week 4

| 53min 50sec total length
  • <?php echo $alt; ?>

    Markov Chains

    10m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Motivation for Sampling - Part - 02

    10m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Why de we care about Markov Chains ?

    10m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Motivation for Sampling

    10m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Computing the gradient of the log likelihood

    10m <?php echo $alt; ?>
NOC:Deep Learning - Part 2

Week 5

| 33min 33sec total length
  • <?php echo $alt; ?>

    Setting up a Markov Chain for RBMs

    11m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Training RBMs Using Gibbs Sampling

    11m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Training RBMS Using Contrastive Divergence

    11m <?php echo $alt; ?>
NOC:Deep Learning - Part 2

Week 6

| 01h 26min total length
  • <?php echo $alt; ?>

    Revisiting Autoencoders

    20m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Variational Autoencoders: The Neural Network Perspective

    20m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Variational Autoencoders: The Graphical model perspective

    46m <?php echo $alt; ?>
NOC:Deep Learning - Part 2

Week 7

| 01h 21min total length
  • <?php echo $alt; ?>

    Neural Autoregressive Density Estimator

    46m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Masked Autoencoder Density Estimator (MADE)

    35m <?php echo $alt; ?>
NOC:Deep Learning - Part 2

Week 8

| 01h 12min total length
  • <?php echo $alt; ?>

    Generative Adversarial Networks - The Intuition

    25m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Generative Adversarial Networks - Architecture

    9m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Generative Adversarial Networks - The Math Behind it

    22m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Generative Adversarial Networks - Some Cool Stuff and Applications

    7m <?php echo $alt; ?>
  • <?php echo $alt; ?>

    Bringing it all together (the deep generative summary)

    8m <?php echo $alt; ?>
show 5 more sections
More Courses by Prof Mitesh Khapra

NOC:Deep Learning

by Prof Mitesh Khapra
0.0 (0)

13 Enrollments

Validity Unlimited

Free