What We Offer?

  • 14 Demos and 2 Industry standard project with self-paced solution explainer

  • Code files and Datasets

  • Unique story style learning

  • Self-paced Highly structured Learning references

Demos

  • Basics of Tensorflow and Keras

  • Models

  • Tensors

  • ANN Intuition 1

  • ANN Intuition 2

  • CNN

  • MLP Image Processing

  • RNN Models

  • RNN Intuition 1

  • RNN Intuition 2

  • Boltzmann Machine Intuition

  • Restricted Boltzmann Machine

Project-1

Movie Review Sentiment Prediction

Your work is to create a deep learning binary classification model that understand the user comments and predict whether the comment is positive or negative review.

Supporting Enterprises Around the Globe

Project-2

Digit Recognition

You need to create a model that could detect the numbers written in vehicle number plate precisely and thereafter security team can integrate your model to campus webcam to detect numbers or digits from number plate. This model should able to recognized digital as well as handwritten digits, because if the vehicles is new, the number plate’s digits may be hand written.

Target Audience

  • Any one who wants to start his journey in Data Science

  • Intermediate or beginner users who want to learn deep learning

Pre-requisites

  • Basic Python programming knowledge is required

Deep Learning with Tensorflow and Keras - Demos and Projects

Price INR 999/-

Course Curriculum

  • 2

    Introduction to Deep Learning

    • Introduction

    • Why deep learning?

    • Brief History about deep learning

    • How industries are getting benefit from deep learning

    • Enhancement in deep learning from past

  • 3

    Fundametals of Keras and Tensoflow

    • Lesson - Introduction

    • What is tensorflow?

    • Why use tensorflow?

    • Tensowflow 1.x vs tensorflow 2.x

    • Tensoflow Installations and Setup

    • Tensorflow Constants and Variables

    • Tensors

    • Placeholder

    • Tensors operations

    • Strings

    • Automatic differentiations

    • Introduction to graphs

    • Tensorflow models

    • What is keras?

    • Why use keras?

    • Keras Key Concepts

    • Keras installation and setup

    • Keras creating models - Sequentials API

    • Model function API

    • Keras callbacks - Model checkpoint

    • Early stopping

    • ReduceLROnPlateau

    • How to convert keras code to tensorflow 2.0

  • 4

    Demo-1 - Introduction

    • Demo - Introduction

    • Demo Resources

  • 5

    Demo-2 - Models

    • Title - Models

    • Resource - Code files and Datasets

  • 6

    Demo-3 - Tensors

    • Title - Tensors

    • Resource - Code files and Datasets

  • 7

    Creating Models and Optimization in Keras and Tensorflow

    • Lesson-3 Introduction

    • Artifical Neural Network Overview

    • The Neuron

    • How neuron works?

    • Hidden layer

    • Activation Function

    • Optimizer

    • Loss Function

    • Gradient Descent

    • Stochastic Gradient Descent

    • Backpropagation

    • What is Perceptrons and overview

    • Drop Out

    • Train a Perceptron

    • Convexity - Basics and properties

    • Gradient descent in once dimention

    • Multivariate Gradient descent

    • Stachastic Gradient descent - Gradient descent update

    • Dynamic learning rate

    • Other optimization and comparisons - Adagrad

    • RMSProps

    • Adam

  • 8

    Demo-4 - ANN Intuition 1

    • Title - ANN Intuition 1

    • Resource - Code files and Datasets

  • 9

    Demo-5 - ANN Intuition 2

    • Title - ANN Intuition 2

    • Resource - Code files and Datasets

  • 10

    Solving Convolutional Neural network with Keras & Tensoflow

    • Lesson Introduction

    • A brief Introduction to Convolutional layer

    • CNN Architecture

    • The role and applications of convolutional layer

    • From Fully connected layer to convolution - Invariance

    • Convolutions

    • Convolution for images - The cross correlation operation

    • Convolutional layer

    • Learning a kernel

    • Feature map and receptive field

    • Padding

    • Stride

    • Relu

    • Maximum pooling and average pooling

    • Flattening of layer

    • Fully connected layer

  • 11

    Demo-6 - CNN

    • Title - CNN

    • Resource - Code files and Datasets

  • 12

    Demo-7 - MLP Image processing

    • Title - MLP Image Processing

    • Resource - Code files and Datasets

  • 13

    Solving Recurrent Neural Network in Keras and Tensorflow

    • Lesson - Introduction

    • Brief Introduction about RNN

    • Idea behind RNN

    • Applications of RNN

    • RNN Intuition - Vanishing Gradient Problem

    • Implementation of RNN - One Hot Encoding

    • Initialize model parameter

    • Gradient Clipping

    • Prediction

    • Back Propagation through time - Analysis of gradient in RNN

    • Back propagation in time in details

    • Modern RNN - GRU

    • Modern RNN - LSTMs

    • Modern RNN - Deep Recurrent neural Networks

  • 14

    Demo-8 - RNN Intuition-1

    • Title - RNN Intuition 1

    • Resource - Code files and Datasets

  • 15

    Demo-9 - RNN Intuition-2

    • Title - RNN Intuition 2

    • Resource - Code files and Datasets

  • 16

    Demo-10 - RNN Models

    • Title - RNN Models

    • Resource - Code files and Datasets

  • 17

    Boltzmann Machine in Keras and Tensorflow

    • Lesson - Introduction

    • What is boltzmann machine and meaning?

    • Bolzmann Machine Intuition

    • Implementation of Bolzmann Machine - Energy based model

    • Restrictive Boltzmann Machine

    • Contrastive divergence meaning

    • Deep boltzmann machine

  • 18

    Demo-11 - Boltsmann Machine Intution

    • Title - Boltzmann Machine Intuition

    • Demo Resources

  • 19

    Demo-12 - Restrictive Boltsmann machine model

    • Title - Restricted Boltzmann Machine

    • Demo Resources

  • 20

    Autoencoders using Keras and Tensorflow

    • Lesson - Introduction

    • What is autoencoders?

    • Training of autoencoders

    • Overcomplete hidden layers

    • Sparse autoencoders

    • Denoising autoencoders

    • Contractive autoencoders

    • Stacked autoencoders

    • Deep autoencoders

  • 21

    Demo-13 - Autoencoders Intuition

    • Title - Autoencoders Intuition

    • Demo Resources

  • 22

    Demo-14 - Autoencoders Use Case Model

    • Title - Autoencoders Usecase

    • Demo Resources

  • 23

    Project-1 - Movie Review Sentiment Prediction

  • 24

    Project-2 - Digit Recognition

FAQ

  • After signing up for the course, after how much time would I get access to the Learning Content?

    As soon as you signed-up, you will have full access to the complete self-paced content.

  • How my doubts will be resolved?

    There is a discussion forum attached to each course in your LMS. You can post your questions and our expert(s) will answer the queries.

  • For how long do I have access to the course material?

    The training course content is available to you for lifetime.

Our Students Love Us.

Vishal Agnihotri

This is my first experience to online learning from learnkarts. The course was very engaging and the support provided was awesome. Overall, it is was a great learning experience and it helped me to get job in Python.

Yana Sri

The instructor of the training explained all the doubts patiently. It is very easy to learn from anywhere without any problem. Online forum support is excellent.

Ankit Vohra

The project was very good. Highly recommend this for anyone looking to learn Python.

Coming soon!

Add your email to the mailing list to get the latest updates.

Related Courses