New Batch On Artificial Intelligence

FOUNDATIONS OF AI/ML: :

• Linear Algebra & Calculus
•  Statistics & Probability
•  PROGRAMMING:Python for AI (Significant Functions, Packages and Routines)

MACHINE LEARNING ALGORITHMS 1 SUPERVISED LEARNING :

•  Regression (Linear, Multiple, Logistic)
•  Classification (k-NN, naïve Bayes) techniques
•  Decision Trees

MACHINE LEARNING ALGORITHMS 2UNSUPERVISED LEARNING

•  Clustering (k-means, hierarchical, high-dimensional)
•  Expectation Maximization

MACHINE LEARNING ALGORITHMS 3 REINFORCEMENT LEARNING :

•  Markov Decision, MonteCarlo Predictions
•  Value-based methods (e.g. Q-learning)
•  Policy-based methods

MACHINE LEARNING ALGORITHMS 4 ENSEMBLE TECHNIQUES :

• Boosting and Bagging
• Random Forests

MACHINE LEARNING FRAMEWORKS 

• SKIKIT LEARN
• TENSORFLOW
• THEANO
• KERAS
• PRTORCH

Python Libraries :

•  Pandas,Numpy,Scipy,Matplotlib etc.,

DEEP LEARNING :

•  Neural Network Basics
•  Deep Neural Networks
•  Recurrent Neural Networks (RNN)
•  Deep Learning applied to Images using CNN

Mini-Project on CV,NLP or Chat bots.