Research Based and Integration Oriented Program in the World

Actual fees INR 3,00,000

ARTH learners NIL

Program Duration

500 hours

In this age of Automation, the traditional concepts and approaches are getting neglected and Technologies like Machine Learning, Artificial Intelligence etc. are getting evolved. This era of digitalization we live in is changing the way we work. The organizations endeavouring to accomplish the comprehensive digital transformation becoming data-driven is a key goal for them.

Become a part of the only program in the world, where the learners will understand the need & the power of integrating Cloud Computing, DevOps and BigData Ecosystem with Machine Learning.

Program is designed to fulfill the current need of industry covering all the aspects of Data Science.

Detailed Content of Machine Learning

What is feature selection?
Filter Methods
Wrapper methods
Embedded Methods
Constant, quasi constant, and duplicated features
Constant features
Quasi-constant features
Duplicated features
Basic methods plus Correlation pipeline
Statistical methods – Intro
Mutual information
Chi-square for categorical variables | Fisher score
Univariate approaches
Univariate ROC-AUC
Wrapper methods – Intro
Step forward feature selection
Step backward feature selection
Exhaustive search
Regularisation – Intro
Regression Coefficients – Intro
Selection by Logistic Regression Coefficients
Coefficients change with penalty
Selection by Linear Regression Coefficients
Selecting Features by Tree importance – Intro
Select by model importance random forests |embedded
Select by model importance random forests | recursively
Select by model importance gradient boosted machines
Feature selection with decision trees | review
Jupyter Overview:
Updates to Notebook Zip
Jupyter Notebooks
Optional: Virtual Environments
Python Core to Advance
Python for Data Analysis - NumPy:
Introduction to Numpy
Numpy Arrays
Array Indexing
Numpy Array Indexing
Numpy Operations
Python for Data Analysis - Pandas:
Introduction to Pandas
Missing Data
Merging Joining and Concatenating
Data Input and Output
Python for Data Visualization - Matplotlib
Python for Data Visualization - Seaborn
Introduction to Seaborn
Categorical Plots
Matrix Plots
Regression Plots
Style and Color
Python for Data Visualization - Pandas Built-in Data Visualization
Pandas Built-in Data Visualization
Pandas Data Visualization Exercise
Pandas Data Visualization Exercise- Solutions
Python for Data Visualization - Plotly and Cufflinks
Plotly and Cufflinks
Python for Data Visualization - Geographical Plotting
Choropleth Maps
Supervised Learning Overview
Bias/Variance Tradeoff
K-Fold Cross-Validation to avoid overfitting
Data Cleaning and Normalization
Normalizing numerical data
Detecting outliers
Feature Engineering and the Curse of Dimensionality
Imputation Techniques for Missing Data
Handling Unbalanced Data: Oversampling, Undersampling, and SMOTE
Binning, Transforming, Encoding, Scaling, and Shuffling
Simple Linear Regression
Simple Linear Regression Intuition
Cross Validation and Bias-Variance Trade-Off
Bias Variance Trade-Off
Multiple Linear Regression
Multiple Linear Regression Intuition
Multiple Linear Regression - Backward Elimination
Multiple Linear Regression - Automatic Backward Elimination
Polynomial Regression
Polynomial Regression Intuition
Support Vector Regression (SVR)
SVR in Python and R
Decision Tree Regression
Decision Tree Regression Intuition
Random Forest Regression
Random Forest Regression Intuition
Evaluating Regression Models Performance
R-Squared Intuition
Adjusted R-Squared Intuition
Interpreting Linear Regression Coefficients
Logistic Regression
Logistic Regression Intuition
K-Nearest Neighbors (K-NN)
K-Nearest Neighbor Intuition
SVM Intuition
Kernel SVM
Kernel SVM Intuition
Types of Kernel Functions
Non-Linear Kernel SVR
Naive Bayes
Naive Bayes Intuition
Decision Tree Classification
Decision Tree Classification Intuition
Random Forest Classification
Random Forest Classification Intuition
Classification Model Selection in Python
Evaluating Classification Models Performance
False Positives & False Negatives
Confusion Matrix
Accuracy Paradox
CAP Curve
CAP Curve Analysis
K-Means Clustering
K-Means Random Initialization Trap
K-Means Selecting The Number Of Clusters
K-Means Clustering
Hierarchical Clustering
Hierarchical Clustering How Dendrograms Work
Association Rule Learning
Apriori Intuition
Eclat Intuition
Reinforcement Learning
Upper Confidence Bound (UCB)
Upper Confidence Bound
Thompson Sampling
Thompson Sampling Intuition
Algorithm Comparison: UCB vs Thompson Sampling
Natural Language Processing
NLP Intuition
Types of Natural Language Processing
Classical vs Deep Learning Models
Bag-Of-Words Model
Introduction to Neural Networks
Introduction to Neural Networks
Introduction to Perceptron
Neural Network Activation Functions
Cost Functions
Gradient Descent Backpropagation
TensorFlow Playground
Manual Creation of Neural Network
Operations / Placeholders and Variables / Session
TensorFlow Basics
Introduction to TensorFlow
TensorFlow Graphs
Variables and Placeholders
TensorFlow - A Neural Network
TensorFlow Regression
TensorFlow Classification
Saving and Restoring Models
Introduction to Artificial Neural Networks (ANN)
Installing Tensorflow
Perceptron Model
Neural Networks
Activation Functions
Multi-Class Classification Considerations
Cost Functions and Gradient Descent
TensorFlow vs Keras
TF Syntax Basics
Deep Learning
Artificial Neural Networks
The Neuron
The Activation Function
How do Neural Networks work?
How do Neural Networks learn?
Gradient Descent
Stochastic Gradient Descent
Business Problem Description
Convolutional Neural Networks
What are convolutional neural networks?
Convolution Operation
ReLU Layer
Full Connection
Softmax & Cross-Entropy
Dimensionality Reduction
Principal Component Analysis (PCA)
Principal Component Analysis (PCA) Intuition
Linear Discriminant Analysis (LDA)
Linear Discriminant Analysis (LDA) Intuition
Kernel PCA
Model Selection & Boosting
k-Fold Cross Validation
Grid Search in Python
Model Selection and Boosting
Recommender Systems
Recommender Systems
Natural Language Processing
Natural Language Processing Theory
Statistics and Probability Refresher, and Python Practice
Mean, Median, Mode
Variation and Standard Deviation
Probability Density Function; Probability Mass Function
Common Data Distributions
Percentiles and Moments
Covariance and Correlation
Conditional Probability
Bayes' Theorem
Recommender Systems
User-Based Collaborative Filtering
Item-Based Collaborative Filtering
Data Warehousing Overview: ETL and ELT
Reinforcement Learning
Reinforcement Learning & Q-Learning with Gym
Understanding a Confusion Matrix
Measuring Classifiers (Precision, Recall, F1, ROC, AUC)
Recurrent Neural Networks (RNN's)
Using a RNN for sentiment analysis
Transfer Learning
Tuning Neural Networks: Learning Rate and Batch Size Hyperparameters
RNN Intuition
The Vanishing Gradient Problem
LSTM and GRU Theory
Evaluating and Improving the RNN
Evaluating the RNN
Improving the RNN
Self Organizing Maps
SOMs Intuition
How do Self-Organizing Maps Work?
Reading an Advanced SOM
Building a SOM
Boltzmann Machines
Boltzmann Machine Intuition
Boltzmann Machine
Energy-Based Models (EBM)
Contrastive Divergence
Deep Belief Networks
Deep Boltzmann Machines
Free Energy
RBM Greedy Layer-Wise Pretraining
The Vanishing Gradient Problem
The Vanishing Gradient Problem Description
Training an Auto Encoder
Overcomplete hidden layers
Sparse Autoencoders
Denoising Autoencoders
Contractive Autoencoders
Stacked Autoencoders
Deep Autoencoders
Word2Vec Theory
Deep Nets with Tensorflow Abstractions API
Deep Nets with Tensorflow Abstractions API - Estimator API
Deep Nets with Tensorflow Abstractions API - Keras
Deep Nets with Tensorflow Abstractions API - Layers
Autoencoder Basics
Dimensionality Reduction with Linear Autoencoder
Linear Autoencoder PCA
Stacked Autoencoder
Denoising Autoencoders
Stacked Autoencoders
Testing greedy layer-wise autoencoder training vs. pure backpropagation
Cross Entropy vs. KL Divergence
Deep Autoencoder Visualization Description
Reinforcement Learning with OpenAI Gym
Introduction to Reinforcement Learning with OpenAI Gym
Introduction to OpenAI Gym
OpenAI Gym Steup
Open AI Gym Env Basics
Open AI Gym Observations
OpenAI Gym Actions
Simple Neural Network Game
Policy Gradient Theory
Policy Gradient Code
GAN - Generative Adversarial Networks
Introduction to GANs
Principal Components Analysis
How does PCA work?
PCA objective function
PCA Application: Naive Bayes
SVD (Singular Value Decomposition)
t-SNE (t-distributed Stochastic Neighbor Embedding)
t-SNE Theory
t-SNE Visualization
t-SNE on the Donut
t-SNE on XOR
Applications to NLP (Natural Language Processing)
Application of PCA and SVD to NLP (Natural Language Processing)
Latent Semantic Analysis in Code
Application of t-SNE + K-Means: Finding Clusters of Related Words
Applications to Recommender Systems
Recommender Systems Section Introduction
Why Autoencoders and RBMs work
Data Preparation and Logistics
Data Preprocessing Code
AutoRec in Code
Categorical RBM for Recommender System Ratings
Generative Modeling Review
What does it mean to Sample?
Sampling Demo: Bayes Classifier
Gaussian Mixture Model Review
Bayes Classifier with GMM
Variational Autoencoders
Variational Autoencoder Architecture
Parameterizing a Gaussian with a Neural Network
The Latent Space, Predictive Distributions and Samples
Cost Function
Tensorflow Implementation
The Reparameterization Trick
Visualizing the Latent Space
Bayesian Perspective
Generative Adversarial Networks (GANs)
GAN - Basic Principles
GAN Cost Function
Batch Normalization Review
Fractionally-Strided Convolution
Tensorflow Implementation
Face Detection Intuition
Haar-like Features
Integral Image
Training Classifiers
Adaptive Boosting (Adaboost)
Face Detection Intuition
Face Detection with OpenCV
Object Detection Intuition
How SSD is different
The Multi-Box Concept
Predicting Object Positions
Image Creation with GANs
Recurrent Neural Networks, Time Series, and Sequence Data
Sequence Data
Autoregressive Linear Model for Time Series Prediction
Proof that the Linear Model Works
Recurrent Neural Networks
RNN Code Preparation
RNN for Time Series Prediction
Natural Language Processing (NLP)
Code Preparation (NLP)
Text Preprocessing
Text Classification with LSTMs
CNNs for Text
Text Classification with CNNs
Recommender Systems
Recommender Systems with Deep Learning
Transfer Learning for Computer Vision
Transfer Learning Theory
Some Pre-trained Models (VGG, ResNet, Inception, MobileNet)
Large Datasets and Data Generators
Deep Reinforcement Learning
Elements of a Reinforcement Learning Problem
States, Actions, Rewards, Policies
Markov Decision Processes (MDPs)
The Return
Value Functions and the Bellman Equation
What does it mean to “learn”?
Deep Q-Learning / DQN
Epsilon-Greedy Theory
Calculating a Sample Mean
Epsilon-Greedy Beginner's Exercise Prompt
Designing Your Bandit Program
Epsilon-Greedy in Code
Comparing Different Epsilons
Optimistic Initial Values Theory
Optimistic Initial Values Code
UCB1 Theory
UCB1 Beginner's Exercise Prompt
UCB1 Code
Bayesian Bandits / Thompson Sampling Theory
Thompson Sampling Code
Thompson Sampling With Gaussian Reward Theory
Thompson Sampling With Gaussian Reward Code
Nonstationary Bandits
Bandit Summary, Real Data, and Online Learning
On Unusual or Unexpected Strategies of RL
From Bandits to Full Reinforcement Learning
Advanced Tensorflow Usage
What is a Web Service?
Tensorflow Serving pt 2
Tensorflow Lite (TFLite)
Training with Distributed Strategies
Using the TPU
In-Depth: Loss Functions
Mean Squared Error
Binary Cross Entropy
Categorical Cross Entropy
In-Depth: Gradient Descent
Gradient Descent
Stochastic Gradient Descent
Variable and Adaptive Learning Rates
Links to TF2.0 Notebooks
VGG and Transfer Learning
Transfer Learning
Relationship to Greedy Layer-Wise Pretraining
ResNet (and Inception)
ResNet Architecture
Building ResNet - Strategy
Building ResNet - Conv Block Details
Building ResNet - Conv Block Code
Building ResNet - Identity Block Details
Building ResNet - First Few Layers
1x1 Convolutions
Different sized images using the same network
Object Detection (SSD / RetinaNet)
What is Object Detection?
The Problem of Scale
The Problem of Shape
Using Pretrained RetinaNet
Neural Style Transfer
Style Transfer Section Intro
Style Transfer Theory
Optimizing the Loss
Class Activation Maps
Object Localization Project
Localization Introduction
Deep NLP Intuition
Seq2Seq Architecture
Seq2Seq Training
Beam Search Decoding
Attention Mechanisms
Building a ChatBot with Deep NLP
Improving & Tuning the ChatBot
Markov Decision Proccesses
MDP Section Introduction
Choosing Rewards
The Markov Property
Markov Decision Processes (MDPs)
Future Rewards
Value Functions
The Bellman Equation
Bellman Examples
Optimal Policy and Optimal Value Function
Dynamic Programming
Intro to Dynamic Programming and Iterative Policy Evaluation
Designing Your RL Program
Gridworld in Code
Iterative Policy Evaluation in Code
Windy Gridworld in Code
Iterative Policy Evaluation for Windy Gridworld in Code
Policy Improvement
Policy Iteration
Policy Iteration in Windy Gridworld
Value Iteration
Monte Carlo
Monte Carlo Intro
Monte Carlo Policy Evaluation
Monte Carlo Policy Evaluation in Code
Policy Evaluation in Windy Gridworld
Monte Carlo Control
Monte Carlo Control in Code
Monte Carlo Control without Exploring Starts
Monte Carlo Control without Exploring Starts in Code
Temporal Difference Learning
Temporal Difference Intro
TD(0) Prediction
TD(0) Prediction in Code
SARSA in Code
Q Learning
Q Learning in Code
TD Summary
Approximation Methods
Approximation Intro
Linear Models for Reinforcement Learning
Monte Carlo Prediction with Approximation
TD(0) Semi-Gradient Prediction
Semi-Gradient SARSA
OpenAI Gym and Basic Reinforcement Learning Techniques
OpenAI Gym Tutorial
Random Search
Saving a Video
CartPole with Bins (Code)
RBF Neural Networks
TD Lambda
N-Step Methods
N-Step in Code
TD Lambda
TD Lambda in Code
TD Lambda Summary
Policy Gradients
Policy Gradient Methods
Policy Gradient in TensorFlow for CartPole
Policy Gradient in Theano for CartPole
Continuous Action Spaces
Deep Q-Learning
Deep Q-Learning Intro
Deep Q-Learning Techniques
Deep Q-Learning in Tensorflow
Pseudocode and Replay Memory
Partially Observable MDPs
Deep Q-Learning Section Summary
A3C - Theory and Outline
Policy Gradient
Twin Delayed DDPG Theory
Introduction and Initialization
The Q-Learning part
The Policy Learning part
The whole training process
Twin Delayed DDPG Implementation
Taking care of Missing Data
Splitting the dataset into the Training set and Test set
Feature Scaling
Encoding Categorical Data