Deep Learning Tensorflow Online Course in Bangalore|India

AI-Deep Learning using TensorFlow

Digging into Neural network, implementation of Deep learning algorithms along with looking over the stacks of data abstraction with the base of Deep learning and TensorFlow trainings.

35, 000 31,495

Courses Description

Digging into Neural network, implementation of Deep learning algorithms along with looking over the stacks of data abstraction with the base of Deep learning and TensorFlow trainings.

  • Fundamentals of Deep Learning
  • Various Deep networks
  • Basics on Neural networks
  • Application of Analytical mathematics on the data
  • Discussion on Backpropagation
  • Knowledge on Autoencoders and varitional Autoencoders
  • Implement different Regression models
  • Courses Curriculum

    Lecture1.1 Introduction to Deep Learning

    Lecture1.2 Necessity of Deep Learning over Machine Learning.

    Lecture1.3 History and evolution of various deep learning algorithms

    Lecture1.4 AI and how is Deep Learning one of the paths to AI in the recent era

    Lecture1.5 Types of Machine Learning and Deep Learning

    Lecture1.6 Why Deep Learning

    Lecture2.1 Working of a Deep Network

    Lecture2.2 What is Perceptron

    Lecture2.3 What is Neuron

    Lecture2.4 Sigmoid neuron

    Lecture2.5 Activation functions

    Lecture2.6 Cost function

    Lecture2.7 Optimization

    Lecture2.8 Dense networks

    Lecture2.9 Regularization

    Lecture2.10 Layered structures

    Lecture2.11 Types of layers

    Lecture2.12 Forward pass

    Lecture2.13 Back propagation - chain rule and evaluation metrics

    Lecture2.14 Gradient Descent

    Lecture2.15 SGD (for a SoftMax classifier example)

    Lecture2.16 Nestorov's momentum

    Lecture2.17 RMSProp

    Lecture2.18 Adam

    Lecture3.1 Introduction to TensorFlow Preview

    Lecture3.2 Advantages of TensorFlow

    Lecture3.3 Vectorization Preview

    Lecture3.4 Variable declaration

    Lecture3.5 Sessions

    Lecture3.6 Graphs

    Lecture3.7 Tensorboard

    Lecture3.8 Implementation of a simple Perceptron in TensorFlow

    Lecture3.9 Implementing a simple feed forward Neural Network in TensorFlow

    Lecture3.10 Various activation functions and their ranges

    Lecture3.11 Pros and cons of Activation functions

    Lecture3.12 Why to use specific activation function

    Lecture3.13 When is the usage of activation function

    Lecture3.14 What are the ones used in industry for specific tasks

    Lecture3.15 Visualization of competition based craft and model results

    Lecture4.1 Introduction to CNN (Convolutional Neural Networks)

    Lecture4.2 Applications of CNN

    Lecture4.3 CNN Architecture

    Lecture4.4 Convolution

    Lecture4.5 Pooling layers

    Lecture4.6 CNN illustrations

    Lecture5.1 Fundamentals of RNN (Recurrent Neural Network)

    Lecture5.2 Applications of RNN

    Lecture5.3 Modelling sequencing

    Lecture5.4 Types of RNNs - LSTM, GRU

    Lectures5.5 Recursive Neural Tensor Network Theory

    Lecture6.1 Introduction of Keras

    Lecture6.2 Understanding of Keras Model Building Blocks

    Lecture6.3 Illustration of different Compositional Layers

    Lectures6.4 Process based use cases’ implementations

    Lecture7.1 Introduction of TFlearn

    Lecture7.2 Understanding of TFlearn Model Building Blocks

    Lecture7.3 Illustration of different Compositional Layers

    Lectures7.4 Step-wise use-cases implementations

    Lecture8.1 ConvNets architecture

    Lecture8.2 Performance evaluations

    Lecture8.3 Hyperparameter search

    Lecture8.4 Auto-monitoring of loss monitoring

    Lecture8.5 Input pre-processing

    Lecture8.6 Productionization of a deep learning pipeline

    Lecture8.7 Cloud workspace set-up for designing a prototype

    Lecture9.1 Application Building

    Reviews