Artificial Intelligence/Machine Learning

AI/ML Course

URGENT: We are starting our new Sundays only batch on This Sunday, 10th July 2022. Please visit our institute (Unit 26, 14th Floor, Bengal Eco Intelligent Park, Block EM, Sector V.) at 10:30am (till 4:30pm) for the FREE Introductory class. Call Nikhil on 8620007775 for ANY Queries.

Join the AI Revolution with this easy AI ML with Deep Learning Course

If you want to explore cutting-edge data science and acquire skills needed to enter the amazing world of ML, this is the right opportunity for you. With average salaries more than 11 Lakhs in India, and the promise of millions of job being created, it makes sense to enter this field ASAP.

The trainer, Nikhil specialises in making difficult concepts look simple, so that even if you are inexperienced, or tired having worked all day, or simply lazy, you will find it easy to learn. Unlike other trainers who skip complicated concepts and are too busy to explain the concepts in depth, Nikhil is loved by his students for taking care that even the weakest student understands well.

By the end of the course, you will

            » Develop a deep understanding of AI & ML
            » Become confident enough to develop AI Apps from scratch on your own
            » Have knowledge experience of a dozed practical AI applications
            » Gain real experience which counts when applying for jobs
            » Get certified as an AI/ML Developer
            » Get placements support with thousands of AI/ML jobs across multiple disciplines

URGENT: We are starting our new Sundays only batch on This Sunday, 10th July 2022. Please visit our institute (Unit 26, 14th Floor, Bengal Eco Intelligent Park, Block EM, Sector V.) at 10:30am (till 4:30pm) for the FREE Introductory class. Call Nikhil on 8620007775 for ANY Queries.


Please note our syllabus below. Please note that while all the topics given here will be covered in full details, there are some part of our syllabus which is kept hidden and will only be revealed to those who join the course. Just like the recipe of KFC is a well protected secret, so are topics in our syllabus.

How to Learn
The Right Mindset
Developing a deep Understanding
Memorizing new concepts fast
Improving Focus & Time Management

What Is Machine Learning?
Why Use Machine Learning?
Types of Machine Learning Systems
Supervised/Unsupervised Learning
Batch and Online Learning
Instance-Based Versus Model-Based Learning
Main Challenges of Machine Learning
Insufficient Quantity of Training Data
Nonrepresentative Training Data
Poor-Quality Data
Irrelevant Features
Overfitting the Training Data
Underfitting the Training Data
Stepping Back
Testing and Validating
Hyperparameter Tuning and Model Selection
Data Mismatch

Working with Real Data
Look at the Big Picture
Frame the Problem
Select a Performance Measure
Check the Assumptions
Get the Data
Create the Workspace
Download the Data
Take a Quick Look at the Data Structure
Create a Test Set
Discover and Visualize the Data to Gain Insights
Visualizing Geographical Data
Looking for Correlations
Experimenting with Attribute Combinations
Prepare the Data for Machine Learning Algorithms
Data Cleaning
Handling Text and Categorical Attributes
Custom Transformers
Feature Scaling
Transformation Pipelines
Select and Train a Model
Training and Evaluating on the Training Set
Better Evaluation Using Cross-Validation
Fine-Tune Your Model
Grid Search
Randomized Search
Ensemble Methods
Analyze the Best Models and Their Errors
Evaluate Your System on the Test Set
Launch, Monitor, and Maintain Your System

Training a Binary Classifier
Performance Measures
Measuring Accuracy Using Cross-Validation
Confusion Matrix
Precision and Recall
Precision/Recall Tradeoff
The ROC Curve
Multiclass Classification
Error Analysis
Multilabel Classification
Multioutput Classification

Linear Regression
The Normal Equation
Computational Complexity
Gradient Descent
Batch Gradient Descent
Stochastic Gradient Descent
Mini-batch Gradient Descent
Polynomial Regression
Learning Curves
Regularized Linear Models
Ridge Regression
Lasso Regression
Elastic Net
Early Stopping
Logistic Regression
Estimating Probabilities
Training and Cost Function
Decision Boundaries
Softmax Regression

Linear SVM Classification
Soft Margin Classification
Nonlinear SVM Classification
Polynomial Kernel
Adding Similarity Features
Gaussian RBF Kernel
Computational Complexity
SVM Regression
Under the Hood
Decision Function and Predictions
Training Objective
Quadratic Programming
The Dual Problem
Kernelized SVM
Online SVMs

Training and Visualizing a Decision Tree
Making Predictions
Estimating Class Probabilities
The CART Training Algorithm
Computational Complexity
Gini Impurity or Entropy?
Regularization Hyperparameters

Voting Classifiers
Bagging and Pasting
Bagging and Pasting in Scikit-Learn
Out-of-Bag Evaluation
Random Patches and Random Subspaces
Random Forests
Feature Importance
Gradient Boosting

The Curse of Dimensionality
Main Approaches for Dimensionality Reduction
Manifold Learning
Preserving the Variance
Principal Components
Projecting Down to d Dimensions
Using Scikit-Learn
Explained Variance Ratio
Choosing the Right Number of Dimensions
PCA for Compression
Randomized PCA
Incremental PCA
Kernel PCA
Selecting a Kernel and Tuning Hyperparameters
Other Dimensionality Reduction Techniques

Limits of K-Means
Using clustering for image segmentation
Using Clustering for Preprocessing
Using Clustering for Semi-Supervised Learning
Other Clustering Algorithms
Gaussian Mixtures
Anomaly Detection using Gaussian Mixtures
Selecting the Number of Clusters
Bayesian Gaussian Mixture Models
Other Anomaly Detection and Novelty Detection Algorithms

From Biological to Artificial Neurons
Biological Neurons
Logical Computations with Neurons
The Perceptron
Multi-Layer Perceptron and Backpropagation
Regression MLPs
Classification MLPs
Implementing MLPs with Keras
Installing TensorFlow 2
Building an Image Classifier Using the Sequential API
Building a Regression MLP Using the Sequential API
Building Complex Models Using the Functional API
Building Dynamic Models Using the Subclassing API
Saving and Restoring a Model
Using Callbacks
Visualization Using TensorBoard
Fine-Tuning Neural Network Hyperparameters
Number of Hidden Layers
Number of Neurons per Hidden Layer
Learning Rate, Batch Size and Other Hyperparameters

Vanishing/Exploding Gradients Problems
Glorot and He Initialization
Nonsaturating Activation Functions
Batch Normalization
Gradient Clipping
Reusing Pretrained Layers
Transfer Learning With Keras
Unsupervised Pretraining
Pretraining on an Auxiliary Task
Faster Optimizers
Momentum Optimization
Nesterov Accelerated Gradient
Adam and Nadam Optimization
Learning Rate Scheduling
Avoiding Overfitting Through Regularization
ℓ1 and ℓ2 Regularization
Monte-Carlo (MC) Dropout
Max-Norm Regularization
Summary and Practical Guidelines

A Quick Tour of TensorFlow
Using TensorFlow like NumPy
Tensors and Operations
Tensors and NumPy
Type Conversions
Other Data Structures
Customizing Models and Training Algorithms
Custom Loss Functions
Saving and Loading Models That Contain Custom Components
Custom Activation Functions, Initializers, Regularizers, and Constraints
Custom Metrics
Custom Layers
Custom Models
Losses and Metrics Based on Model Internals
Computing Gradients Using Autodiff
Custom Training Loops
TensorFlow Functions and Graphs
Autograph and Tracing
TF Function Rules

The Data API
Chaining Transformations
Shuffling the Data
Preprocessing the Data
Putting Everything Together
Using the Dataset With tf.keras
The TFRecord Format
Compressed TFRecord Files
A Brief Introduction to Protocol Buffers
TensorFlow Protobufs
Loading and Parsing Examples
Handling Lists of Lists Using the SequenceExample Protobuf
The Features API
Categorical Features
Crossed Categorical Features
Encoding Categorical Features Using One-Hot Vectors
Encoding Categorical Features Using Embeddings
Using Feature Columns for Parsing
Using Feature Columns in Your Models
TF Transform
The TensorFlow Datasets (TFDS) Project

The Architecture of the Visual Cortex
Convolutional Layer
Stacking Multiple Feature Maps
TensorFlow Implementation
Memory Requirements
Pooling Layer
TensorFlow Implementation
CNN Architectures
Implementing a ResNet-34 CNN Using Keras
Using Pretrained Models From Keras
Pretrained Models for Transfer Learning
Classification and Localization
Object Detection
Fully Convolutional Networks (FCNs)
You Only Look Once (YOLO)
Semantic Segmentation

Predict Housing Price
Stock Price Prediction
Online Assignment Plagiarism Checker
Personality Prediction System via CV Analysis
Breast Cancer Detection
Undersea Sonar Bomb Detection
Handwriting Recognition
Face recognition
YouTube Comment Spam Detection
11. Face Filter

Secrets of Success
SUpercharged CVs
Technical & HR Interview Preperation
Speaking & giving Presentations on AI
Freelancing / Entrepreneurship

What is YOUR Benefit in Machine Learning?

Unless you have been learning nothing, you already know that AI/ML is the MOST advanced technology mankind has ever made. Stephen Hawking, Elon Musk, Bill Gates etc have all indicated that AI is the future, as such, this is the MOST advantageous yet dangerous technology as well. The Indian IT Industry, heavily unbalanced towards the service sector, is in grave danger and millions are jobs are going to be lost when the tsunami of AI comes suddenly. The false sense of safety you feel in a big MNC is an illusion, just like it seemed at one time that the huge dinosaurs with their power and intelligence would rule the world, but they could not adapt and disappeared completely. No One is Safe.

However, with great changes also comes great potentials. Here are the top ten benefits to you:

1. Open New Doors: Unlike normal software jobs where you feel stuck and with no real learning, AI will open new horizons to you where sky is the limit. Get job offers like never before!

2. Multiply you salary: There are cases where people like you working on older technologies got three time the salary within a year when they learned and shifted to AI.

3. Be an Entrepreneur: If you want to start your business, an emerging superpower like AI is the best bet. You can simply ride on its success without having to put in much effort, investment. This is the Right technology at the Right time, which is Right now.

4. Uncover your potentials: Many highly intelligent programmers lose their talents since their jobs gives them repetitive mundane work. In this world, you lose what you don't use. If you tie up and don't use your hand for a long time, you will lose it. Similarly, the creativity inside people die since they do not get to really use it. AI on the other side, is the MOST creative area and it will take your creativity to new levels everyday.

5. Do Power Programming: In AI, you don't work on boring Forms, Reports and Access controls all day. You don't work on Desktops or Servers. You work at a humongous level, you syndicate the supercomputers of the cloud, and build powerful systems that harness insane amounts of data and processing.

6. Beat the Competition: With millions of software developers in India, it makes sense to shift to the latest technology with the least competition. Salaries follow the economic principles of demand supply, since the new AI has less supply of programmers and huge demand, you can easily beat the competition and earn super high.

7. Show them what you really are: There is no respect for software developers today, simply due to too high quantity. The only way you can stand out is to focus on Quality, and which Technology is more advanced and high quality compared to AI? None! AI Developers are highly appreciated and respected. Join Them. Join our Workshop.

8. Enter Robotics: When you learn AI and have a knack for Electronics too, you can enter the field of Robotics - the Future of the world itself. The earlier you start, the more established you will be when the age of robots come.

9. Build Expert, Complex Systems: Traditional programming, being centered around Loops and Conditions, are very backward and useless for certain kind of problems. Imagine - you may be a great programmer - but if I ask you to write a program that differentiates your mothers picture from those of other women, you will find that you cant even think of the algorithm. AI Lets you build such systems in a few minutes!

10. Fall in Love with technology again: Remember those school days when you got to do amazing experiments, made wonderful projects that gave you the satisfaction of creating something on your own. The platform of AI is designed like that - no copy paste tasks, focus on innovation and ideas. Feel like a kid with Lego toys again. Let loose your creativity.

The Dangers: Important - All regular jobs are going to get automated sooner or later. It is not if, but a question of when your job will be taken over by machines. If you are already not aware of the seriousness of the problem, well, a wise man did say - Ignorance is Bliss.