forum

Have Questions? 8373 99 4242 or 8860 93 4343

Free Session


Deep Learning - The Beginning of A.I.

 
Module 1: INTRODUCTION OF DEEP LEARNING WITH TENSORFLOW

Motivation for Machine Learning?
Limitations of Machine Learning?
Revolution of Artificial Intelligence
Motivation for Deep Learning?
Advantages of Deep Learning over Machine Learning
Real-life use cases of Deep Learning
Required Linear Algebra and Statistics

Module 2: INTRODUCTION OF ARTIFICIAL NEURAL NETWORKS (DEEP LEARNING)

Deep Learning: A revolution in Artificial Intelligence
What is Neural Networks and Historical background?
Neural networks vs. conventional computers
Basic Structure of ANNs
How neural networks works?

Module 3: DEEP LEARNING DIFFERENT OPEN SOURCE PROJECTS
  • TENSORFLOW (GOOGLE)
  • TORCH (FACEBOOK)
  • CNTK (MICROSOFT)
  • NNABLA (SONY)
  • AFFLINE (OPEN SOURCE)
Module 4: MACHINE & DEEP LEARNING ALGORITHMS
supervised learning - (deep learning)

 

Convolutional neural networks /> Recurrent neural networks
Reinforcement learning
Transfer learning

  • Regression
  • Naive Bayes - Probabilistic Classifier
  • K-Nearest Neighbours - Non-Probabilistic Classifier
  • Support Vector Machines (SVM)
Module 5: MATH: LINEAR ALGEBRA

Scalars, Vectors, Matrices
Tensors, Hyperplanes
Standard Deviation
Gradient descent and Cost function
Hypothesis function

Module 6: STATISTICS: Machine Learning

Probability and Conditional Probabilities
Posterior Probability
Distributions
Resampling Methods
Selection Bias
Likelihood

Module 7: DEEP LEARNING: TENSORFLOW

How Deep Learning Works?.
Neural Networks in deep learning
Activation and loss Functions
Gradient Descent
Illustrate and Training Perceptron
Real-Life Parameters of Perceptron
Implementation of Multi-Layer Perceptron
limitations of A Single Perceptron
Backpropagation – Learning Algorithm
Backpropagation – Using Neural Network Example
Firing rules - How neurones make decisions

Module 8: TENSORFLOW: IMPLEMENT DEEP LEARNING

What is Tensorflow and use of TensorFlow in Deep Learning?
Installation of Tensorflow
Tensorflow code-basics
Constants, Placeholders, Variables Scope, Graph,
Creating and Saving a Model
Re-Store a Model
Running a simple ML algorithm on TensorFlow
Tensor Board: Graph Visualization
Tensor Projector: Training pipe line visualization
MLP Digit-Classifier using TensorFlow
Step by Step - Use-Case Implementation

Module 9: LINEAR & LOGISTIC REGRESSION

Understanding the context of Regression
Type of Regression

  • Linear Regression
  • Logistic Regression
  • Multiple Regression

Model evaluation:

  • Regression standard error
  • R-squared
  • Testing the slope

Regression model to estimate and predict values

Selecting the best regression equation

Module 10: NAIVE BAYES - PROBABILISTIC CLASSIFIER

What is probability distribution
Random variable? & Types of Random variable?
Bayes Theorem - Probabilistic Theorem?
What is conditional probability?
Use Naive Bayes with python/Tensorflow.
Linear Regression with Multiple Variables

Module 11: KERAS: A HIGH LEVEL API

Introduction to Keras
Keras vs TFLearn
compose models in Keras
Sequential and Functional Composition
Predefined Neural Network Layers
Using Inception v3 Predefined model
Batch Normalization: Keras
Saving and Loading a model with Keras
Customizing the Training Process
Tensor Board: With Keras
Use-Case Implementation with Keras

Module 12: K-NEAREST NEIGHBOURS - NON-PROBABILISTIC CLASSIFIER

What is KNN classifier?
Calculate K in KNN?
Kind of problem instance in KNN
Difference between Naive Bayes & KNN
Definition of distance
Data reduction & Dimensionality Reduction?
Feature extraction in KNN

Module 13: SUPPORT VECTOR MACHINES (SVM)

Learn the simple intuition behind Support Vector Machines.
Implement an SVM classifier in SKLearn/scikit-learn
Choose the right kernel for your SVM
Learn about RBF and Linear Kernels

Module 14:IMAGE: CONVOLUTIONAL NEURAL NETWORKS

Introduction to CNN
Train a simple convolutional neural net
Explore the design space for convolutional nets
Pooling layer motivation in CNN
Design a convolutional layer application
Understanding and Visualizing a CNN
Transfer Learning and Fine-tuning CNN
Deep convolutional neural net

Module 15: RECURRENT NEURAL NETWORKS

Introduction to RNN Model
Real-Life use cases of RNN
Modelling sequences
Training RNNs with Backpropagation
Long Short-Term memory (LSTM)
Recursive Neural Tensor Network Theory
Recurrent Neural Network Model

Module 16: Reinforcement Learning: Begining of A.I.

Introduction to Reinforcement Learning
Markov Decision Processes
Dynamic Programming
Monte Carlo Methods
Policy Gradient Methods
Temporal Difference Learning
RBF Networks with Mountain Car
OpenAI Gym and Basic Reinforcement Learning Techniques
OpenAI Gym Tutorial

Module 17: DEEP LEARNING: WITH OUT CODE

Develop deep learning with Zero Code:

PREREQUISITES
None

Fees: 37,999 Rs/-
Duration: 3 Months

PREREQUISITES

None

 

Fees: 37,999 Rs/-
Duration: 3 Months

 

Contact Us

  • Address(Delhi): 4-B Pusa Road, Near Karol bagh Metro Station, Delhi-110005 India

  • Address(Noida): 3rd Floor, Bhagwan Sahai Tower, Sector 15, Noida, UP-201301 India

  • Phone: (Delhi)+91-8373994242, (Noida)+91-8860934343

  • Email: (Delhi) contact@mappingminds.org, (Noida) info@mappingminds.org

Follow Us