Deep Learning III

  • Home
  • Deep Learning III
Trainig and Internship

Introduction to Deep Learning with Python

What you'll learn
  • All the concepts GAN
  • Reinforcement learning
  • Encoders & Decoders
Highlights
  • Certifications – Certificate will be provide after complication of the course.
  • Available –Online / Offline Learning (No recorded lecture / live session of each class).
  • 60 hrs Course..
  • Rich course content for master learning
  • Pay after six demo class.
  • 100% Hands on Course + 30 %Theory.
  • One MCQ and one case study is compulsory for completion of course..
  • Certificate will generated after successfully completion of the course.
Prerequisites
  • Mathematics and Statistics.
  • Python
  • Machine learning
  • Deep learning

Module-1

Probability Theory, Joint Distributions, Represent the joint distribution more compactly, graphical representation of joint distribution, Different types of reasoning encoded in a Bayesian Network, Independencies encoded by a Bayesian Network .

Module-2

Markov Networks: Motivation, Factors in Markov Network, Local Independencies in a Markov Network, Computing the gradient of the log likelihood, Sampling, Concept of a latent variable, Restricted Boltzmann Machines, RBMs as Stochastic Neural Networks, Unsupervised Learning with RBMs, Markov Chains, Setting up a Markov Chain for RBMs, Training RBMs Using Gibbs Sampling, Training RBMS Using Contrastive Divergence.

Module-3

Autoencoders, VariationalAutoencoders, Graphical model perspective, Neural Autoregressive Density Estimator (NADE), Masked Autoencoder Density Estimator (MADE), Generative Adversarial Networks.

Module-4

Introduction to Reinforcement Learning, Bandit algorithms, Policy gradient methods, Dynamic programming and Monte carlo method, Model free prediction and control, DNQ Learning, Actor critics, Case study in RL.

whatsapp