ARTIFICIAL INTELLIGENCE

ARTIFICIAL INTELLIGENCE

Pre-Program Preparation

 

• Python for Data Analysis: Get acquainted with Data Structures, Object Oriented Programming, Data Manipulation and Data Visualization in Python

• Application on Raspberry Pi 3.0

• Introduction to SQL: Learn SQL for querying information from databases

• Math for Data Analysis: Brush up your knowledge of Linear Algebra, Matrices, Eigen Vectors and their application for Data Analysis

 

Statistics Essentials

 

• Inferential Statistics: Learn Probability Distribution Functions, Random Variables, Sampling Methods, Central Limit Theorem and more to draw inferences

• Hypothesis Testing: Understand how to formulate and test hypotheses to solve business problems

• Exploratory Data Analysis: Learn how to summarize data sets and derive initial insights

 

Machine Learning

 

• Linear Regression: Learn to implement linear regression and predict continuous data values- electrical processor based hardware for application

• Supervised Learning: Understand and implement algorithms like Naive Bayes and Logistic Regression- Industrial GUI tool will be used for demonstration

• Unsupervised Learning: Learn how to create segments based on similarities using K-Means and Hierarchical clustering

• Support Vector Machines: Learn how to classify data points using support vectors

• Decision Trees: Tree-based model that is simple and easy to use. Learn the fundamentals on how to implement them

 

Natural Language Processing

 

• Basics of text processing: Get started with the Natural language toolkit, learn the basics of text processing in python

• Lexical processing: Learn how to extract features from unstructured text and build machine learning models on text data

• Syntax and Semantics: Conduct sentiment analysis, learn to parse English sentences and extract meaning from them

• Other problems in text analytics: Explore the applications of text analytics in new areas and various business domains

 

Neural Networks & Deep Learning

 

• Information flow in a neural network: Understand the components and structure of artificial neural networks

• Training a neural network: Learn the cutting-edge techniques used to train highly complex neural networks

• Convolutional Neural Networks: Use CNN's to solve complex image classification problems

• Recurrent Neural Networks: Study LSTMs and RNN's applications in text analytic

• Creating and deploying networks using Tensorflow and keras: Build and deploy your own deep neural networks on a website, learn to use the Tensorflow API and Keras

 

Graphical Models

 

• Directed and Undirected Models: Learn the basics of directed and undirected graphs

• Inference: Learn how graphical models are used to draw inferences using datasets

• Learning: Learn how to estimate parameters and structure of graphical models

 

Reinforcement Learning

 

• Introduction to RL: Understand the basics of RL and its applications in AI

• Markov Decision Processes: Model processes as Markov chains, learn algorithms for solving optimisation problems

• Q-learning: Write Q-learning algorithms to solve complex RL problems