Artificial Intelligence Training Course in Dallas, USA

Motivation- Linear Algebra
Representation of problems in Linear Algebra
Matrix representations and its operations
Eigen values & Eigen vectors
Singular Value Decompositions of a Matrix

Feature Scaling
Feature Standardization
Label Encoding
One Hot Encoding

Steps of Data Exploration & Preparation
Missing Value Treatment
Techniques of Outlier Detection & Treatment
Art of Feature Engineering

What is Machine Learning
Examples of Machine Learning
Supervised, Unsupervised & Reinforcement learning
Difference between Unsupervised & Supervised learning
Nomenclature
Classification
Supervised learning pipeline
Linear Regression
Logistic Regression
Decision Tree
Support Vector Machine
Naive Bayes
K Nearest Neighbors
K- Means
Random Forest
Dimensionality Reduction methods
Gradient Boosting Algorithms- GBM, XGBoost, Light GBM, CatBoost
Case Study with live implementation of the above algorithms in Python

Introduction
Derivatives

• Geometric definition
• Taking the derivative
• Step-by-Step
• Machine learning use cases

Chain Rule:

• How it works
• Step-by-Step
• Multiple functions

Gradients:

• Partial derivatives
• Step-by-Step
• Directional Derivatives
• Useful Properties

Integrals

• Computing integrals
• Applications of Integrations

Biological Neuron
Artificial Neural Network
Layered Networks
Neural Network Applications
The simplest model-Perceptron
Second Generation Neural Networks
Back Propagation Algorithm
Why Deep layered Neural Network
2006 Breakthrough
Unsupervised greedy layer wise training procedure
Layer wise unsupervised Pre-training
Layer wise local unsupervised learning
Experiments
Classification errors on MNIST training
Experiments
Conclusions
Applications
Recent Deep learning HighlightsBiological Neuron
Artificial Neural Network
Layered Networks
Neural Network Applications
The simplest model-Perceptron
Second Generation Neural Networks
Back Propagation Algorithm
Why Deep layered Neural Network
2006 Breakthrough
Unsupervised greedy layer wise training procedure
Layer wise unsupervised Pre-training
Layer wise local unsupervised learning
Experiments
Classification errors on MNIST training
Experiments
Conclusions
Applications
Recent Deep learning Highlights

When to apply neural networks
General Way to solve problems using Neural Networks
Understanding Image data and popular libraries to solve it
What is TensorFlow
A typical flow of Tensorflow
Implementing Multi-Layer perceptron in Tensorflow
Limitations of Tensorflow
Tensorflow vs other Libraries

Introduction to Keras
Advantages of using Keras
Limitations of using Keras
General way to solve problems with Neural Networks
Starting with a simple Keras implementation on “Identify the Digits”
Hyperparameters to look for in Neural Networks
Parameter fine tuning
Transfer Learning using keras

An overview of PyTorch
Diving into technicalities
Building a neural network in Numpy vs PyTorch
Comparison of PyTorch with other deep learning libraries
Solving an image recognition problem with PyTorch
Transfer learning using PyTorch