Artificial Intelligence Master's Program

·       Need of Machine Learning

·       Introduction to Machine Learning

·       Types of Machine Learning, such as supervised, unsupervised, and reinforcement learning, Machine Learning with Python, and the applications of Machine Learning

·        Introduction to supervised learning and the types of supervised learning, such as regression and classification

·        Introduction to regression

·        Simple linear regression

·        Multiple linear regression and assumptions in linear regression

·        Math behind linear regression

·        Introduction to classification

·        Linear regression vs logistic regression

·        Math behind logistic regression, detailed formulas, the logit function and odds, confusion matrix and accuracy, true positive rate, false positive rate, and threshold evaluation with ROCR

·        Introduction to tree-based classification

·        Understanding a decision tree, impurity function, entropy, and understanding the concept of information gain for the right split of node

·        Understanding the concepts of information gain, impurity function, Gini index, overfitting, pruning, pre-pruning, post-pruning, and cost-complexity pruning

·        Introduction to ensemble techniques, bagging, and random forests and finding out the right number of trees required in a random forest

·        Introduction to probabilistic classifiers

·        Understanding Naïve Bayes and math behind the Bayes theorem

·        Understanding a support vector machine (SVM)

·        Kernel functions in SVM and math behind SVM

·        Types of unsupervised learning, such as clustering and dimensionality reduction, and the types of clustering

·        Introduction to k-means clustering

·        Math behind k-means

·        Dimensionality reduction with PCA

·        Introduction to Natural Language Processing (NLP)

·        Introduction to text mining

·        Importance and applications of text mining

·        How NPL works with text mining

·        Writing and reading to word files

·        Language Toolkit (NLTK) environment

·        Text mining: Its cleaning, pre-processing, and text classification

·        What is time series? Its techniques and applications

·        Time series components

·        Moving average, smoothing techniques, and exponential smoothing

·        Univariate time series models

·        Multivariate time series analysis

·        ARIMA model and time series in Python

·        Sentiment analysis in Python (Twitter sentiment analysis) and text analysis

·       Field of machine learning, its impact on the field of artificial intelligence

·       The benefits of machine learning w.r.t. Traditional methodologies

·       Deep learning introduction and how it is different from all other machine learning methods

·       Classification and regression in supervised learning

·       Clustering and association in unsupervised learning, algorithms that are used in these categories

·       Introduction to ai and neural networks

·       Machine learning concepts

·       Supervised learning with neural networks

·       Fundamentals of statistics, hypothesis testing, probability distributions, and hidden markov models.

·       Multi-layer network introduction, regularization, deep neural networks

·       Multi-layer perceptron

·       Overfitting and capacity

·       Neural network hyperparameters, logic gates

·       Different activation functions used in neural networks, including relu, softmax, sigmoid and hyperbolic functions

·       Back propagation, forward propagation, convergence, hyperparameters, and overfitting.

·       Various methods that are used to train artificial neural networks

·       Perceptron learning rule, gradient descent rule, tuning the learning rate, regularization techniques, optimization techniques

·       Stochastic process, vanishing gradients, transfer learning, regression techniques,

·       Lasso l1 and ridge l2, unsupervised pre-training, xavier initialization.

·       Understanding how deep learning works

·       Activation functions, illustrating perceptron, perceptron training

·       multi-layer perceptron, key parameters of perceptron;

·       Tensorflow introduction and its open-source software library that is used to design, create and train

·       Deep learning models followed by google’s tensor processing unit (tpu) programmable ai

·       Python libraries in tensorflow, code basics, variables, constants, placeholders

·       Graph visualization, use-case implementation, keras, and more.

·       Keras high-level neural network for working on top of tensorflow

·       Defining complex multi-output models

·       Composing models using keras

·       Sequential and functional composition, batch normalization

·       Deploying keras with tensorboard, and neural network training process customization.

·       Using tflearn api to implement neural networks

·       Defining and composing models, and deploying tensorboard

·       Mapping the human mind with deep neural networks (dnns)

·       Several building blocks of artificial neural networks (anns)

·       The architecture of dnn and its building blocks

·       Reinforcement learning in dnn concepts, various parameters, layers, and optimization algorithms in dnn, and activation functions.

·       What is a convolutional neural network?

·       Understanding the architecture and use-cases of cnn

·       ‘What is a pooling layer?’ how to visualize using cnn

·       How to fine-tune a convolutional neural network

·       What is transfer learning?

·       Understanding recurrent neural networks, kernel filter, feature maps, and pooling, and deploying convolutional neural networks in tensorflow.

·       Introduction to the rnn model

·       Use cases of rnn, modeling sequences

·       Rnns with back propagation

·       Long short-term memory (lstm)

·       Recursive neural tensor network theory, the basic rnn cell, unfolded rnn,  dynamic rnn

·       Time-series predictions.

·       Gpu’s introduction, ‘how are they different from cpus?,’ the significance of gpus

·       Deep learning networks, forward pass and backward pass training techniques

·       Gpu constituent with simpler core and concurrent hardware.

·       Introduction rbm and autoencoders

·       Deploying rbm for deep neural networks, using rbm for collaborative filtering

·       Autoencoders features and applications of autoencoders.

·       Image processing

·       Natural language processing (nlp) – Speech recognition, and video analytics.

·        Automated conversation bots leveraging any of the following descriptive techniques:  Ibm watson, Microsoft’s luis, Open–closed domain bots,

·        Generative model, and the sequence to sequence model (lstm).

·       Introduction to Natural Language Processing (NLP)

·       Introduction to Text Mining

·       importance and applications of Text Mining

·       how NPL works with Text Mining, writing and reading to word files,

·       OS Module

·       Natural Language Toolkit (NLTK) Environment

·       Various Tokenizers

·       Tokenization

·       Frequency Distribution

·       Stemming

·       POS Tagging

·       Lemmatization

·       Bigrams

·       Trigrams & Ngrams

·       Lemmatization

·       Entity Recognition

·       Overview of Machine Learning

·       Words

·       Term Frequency

·       Count Vectorizer

·       Inverse Document Frequency

·       Text conversion

·       Confusion Matrix

·       Naiive Bayes Classifier

·       Language Modelling

·       Sequence Tagging

·       Sequence Tasks

·       Predicting Sequence of Tags

·       Syntax Trees

·       Context-Free Grammars

·       Chunking

·       Automatic Paraphrasing of Texts

·       Chinking

·       Distributional Semantics

·       Traditional Models

·       Tools for sentence and word embeddings

·       An overview of Topic Models

·       Introduction to task-oriented Dialog Systems

·       Natural Language Understanding

·        Dialog Manager

·       Introduction rbm and autoencoders

·       Deploying rbm for deep neural networks, using rbm for collaborative filtering

·       Autoencoders features and applications of autoencoders.

·       Constructing a convolutional neural network using TensorFlow

·       Convolutional, dense, and pooling layers of CNNs

·       Filtering images based on user queries

·       Automated conversation bots leveraging

·       Generative model, and the sequence to sequence model (lstm).

·       Parallel Training

·       Distributed vs Parallel Computing

·       Distributed computing in Tensorflow

·       Introduction to tf.distribute

·       Distributed training across multiple CPUs

·       Distributed Training

·       Distributed training across multiple GPUs

·       Federated Learning

·       Parallel computing in Tensorflow

·       Mapping the human mind with deep neural networks (dnns)

·       Several building blocks of artificial neural networks (anns)

·       The architecture of dnn and its building blocks

·       Reinforcement learning in dnn concepts, various parameters, layers, and optimization algorithms in dnn, and activation functions.

·       Understanding model Persistence

·       Saving and Serializing Models in Keras

·       Restoring and loading saved models

·       Introduction to Tensorflow Serving

·       Tensorflow Serving Rest

·       Deploying deep learning models with Docker & Kubernetes