DITTIS Eligibility:
Graduate in Engineering (10+2+4 or 10+3+3 years) in IT / Computer Science / Electronics / Telecommunications / Electrical / Instrumentation. OR MSc/MS (10+2+3+2 years) in Computer Science, IT, Electronics.
Mathematics in 10+2 (exempted for candidates with Diploma + Engineering) OR
Post Graduate Degree in Mathematics/ Statistics/ Physics, OR
MCA
The candidate must have 60% in the qualifying degree.
Detail Syllabus :
Fundamental of Artificial Intelligence
Introduction to AI, Evolution & Revolution of AI, Introduction of Applications in various Domains (Scientific including Health Sciences, Engineering, Financial Services and other industries), Intelligent Agents, Uninformed Search, Constraint Satisfaction Search, Combinatorial Optimization Problems, Heuristic & Meta-heuristics, Genetic Algorithms for Search, Adversarial Search , Parallel Search, Search Engines, Game Theory, various problems, Game Trees, Knowledge Representation and Automated, Propositional and Predicate Logic, Inference and Resolution for Problem Solving, Rules and Expert Systems, Artificial Life, Learning through, Emergent Behavior, Genetic Algorithms, Planning & Planning Methods, Advanced Knowledge Representation, Fuzzy Logic.
Advanced Programming using R & Python
R Programming: Introduction & Installation of R, R Basics, Finding Help, Code Editors for R, Command Packages, Manipulating and Processing Data in R, Reading and Getting Data into R, Exporting Data from R, Data Objects, Data Types & Data Structure. Viewing Named Objects, Structure of Data Items, Manipulating and Processing Data in R (Creating, Accessing , Sorting data frames, Extracting, Combining, Merging, reshaping data frames), Control Structures, Functions in R (numeric, character, statistical), working with objects, Viewing Objects within Objects, Constructing Data Objects, Building R Packages, Running and Manipulating Packages, Non parametric Tests- ANOVA, chi-Square, t-Test, U-Test, Introduction to Graphical Analysis, Using Plots(Box Plots, Scatter plot, Pie Charts, Bar charts, Line Chart), Plotting variables, Designing Special Plots, Simple Liner Regression, Multiple Regression, Interactive reporting with R markdown.
Python Programming:
Introduction to Python, Basic Syntax, Data Types, Variables, Operators, Input/output, Flow of Control (Modules, Branching), If, If- else, Nested if-else, Looping, For, While, Nested loops, Control Structure, Break, Continue, Pass, Strings and Tuples, Accessing Strings, Basic Operations, String slices, Working with Lists, Introduction, Accessing list, Operations, Function and Methods, Files, Modules, Dictionaries, Functions and Functional Programming, Declare, assign and retrieve values from Lists, Introducing Tuples, Accessing tuples, matplotlib, seaborn,
Advanced Python: Object Oriented, OOPs concept, Class and object, Attributes, Inheritance, Overloading, Overriding, Data hiding, Operations Exception, Exception Handling, Python Libraries, Data migration and visualization: Pandas and Matplotlib, Database Interaction in Python,
Case Studies: Mathematical computing with Python, Data migration and visualization: Pandas and Matplotlib, Pycharm, Anaconda, Data manipulation with Pandas
Mathematics & Statistics for Artificial Intelligence
Probability
Basic rules and axioms, events, sample space, frequentist approach, dependent and independent events, conditional probability, Random variables, continuous and discrete, expectation, variance, distributions- joint and conditional, Bayes’ Theorem, MAP, MLE, Popular distributions- binomial, bernoulli, poisson, exponential, Gaussian, Conjugate priorsst
Linear Algebra
Vectors, definition, scalars, addition, scalar multiplication, inner product (dot product), vector projection, cosine similarity, orthogonal vectors, normal and orthonormal vectors, vector norm, vector space, linear combination, linear span, linear independence, basis vectors
·Matrices definition, addition, transpose, scalar multiplication, matrix multiplication, matrix multiplication properties, hadamard product, functions, linear transformation, determinant, identity matrix, invertible matrix and inverse, rank, trace, popular type of matrices- symmetric, diagonal, orthogonal, orthonormal, positive definite matrix
·Eigenvalues & eigenvectors, concept, intuition, significance, how to find Principle component analysis, concept, properties, applications
· Singular value decomposition, concept, properties, applications
Calculus
·Functions, Scalar derivative, definition, intuition, common rules of differentiation, chain rule, partial derivatives, Gradient, concept, intuition, properties, directional derivative
· Vector and matrix calculus, how to find derivative of scalar-valued, vector-valued function with respect to scalar, vector} four combinations- Jacobian
· Gradient algorithms, local/global maxima and minima, saddle point, convex functions, gradient descent algorithms- batch, mini-batch, stochastic, their performance comparison
Miscellaneous Topics
Information theory, entropy, cross entropy, KL divergence, mutual information
Markov Chain, definition, transition matrix, stationarity.
Statistics:
Descriptive Statistics, Summary Statistics Basic probability theory, Statistical Concepts (uni-variate and bi-variate sampling, distributions, re-sampling, statistical Inference, prediction error), Probability Distribution(Continuous and discrete- Normal, Bernoulli, Binomial, Negative Binomial, Geometric and Poisson distribution),Bayes’ Theorem, Central Limit theorem, Data Exploration & preparation, Concepts of Correlation, Regression, Covariance, Outliers etc.
Machine Learning
Introduction to machine learning and need The Learning Problem, Terminology, Canonical Learning Problems, Supervised Learning, Unsupervised Learning, Reinforcement Learning, ML applications in the real world, A key ML concept, Uses of Machine learning , Introduction to feature engineering, raw data to feature, Data Preparation ,feature creation, Data cleaning & transformation, Data Validation & Modelling, Feature selection Techniques, Dimensionality reduction, PCA, Ensemble methods ,Bagging & Boosting , ML Algorithms, Decision Trees, Oblique trees, Random forest, Bayesian analysis and Naïve bayes classifier, Support vector Machines , KNN, Gradient boosting , Association rules learning, Apriori and FP growth algorithms, Linear and Non liner classification, linear and logistic Regression, Clustering ,K-means ,Overview of Factor Analysis, ARIMA, ML in real time , Algorithm performance metrics , ROC ,AOC, Confusion matrix , F1 score, MSE, MAE.
Machine Learning Tools: introduction to the basic data science toolset
Case Studies:
· Usage of ML algorithms, Algorithm performance metrics (confusionmatrixsensitivity,specivity,ROC,AOC,F1score,Precision,Recall,MSE,MAE),
· Implementation of case studies will be using R / Weka.
· Implementation of ML algorithms using high level api like Scikit-learn.
· Credit Card Fraud Analysis , Intrusion Detection system,
· Implement basic gradient descent in Tensor Flow.
Data Analytics
Introduction to Data Analytics Descriptive Statistical Measures, Probability Distribution and Data, Sampling and Estimation, Predictive modelling and analysis, Regression Analysis, Forecasting Techniques, Simulation and Risk Analysis, Optimization, Linear, Non linear, Integer, Decision Analysis, Making Right Business Decisions based on data, Exploratory Data Analysis, Visualization and Exploring Data, Text analytics, Social network analysis, web scrapping, Dimensionality issues, Ridge & lasso regression, bias/variance trade off, density, PCA, FA, Directional Data Analytics, Functional Data Analysis, Data Analysis & visualization – using numpy, matplotlib, scipy, Advanced python packages.
Reinforcement Learning
Introduction to reinforcement learning as an approximate dynamic programming problem, Overview of reinforcement learning: the agent environment framework, successes of reinforcement learning, Bandit problems and online learning, Markov decision processes, Returns, and value functions, Solution methods: dynamic programming, Solution methods for learning, Solution methods for temporal difference learning, Eligibility traces, Value function approximation Models and planning (table lookup case),
Case studies: successful examples of RL systems, simulation based methods like Q-learning.
Deep Neural Networks
Introduction to Deep Neural Network, RNN, CNN ,LSTM, Deep Belief Network, semantic Hashing, Training deep neural network, introduction to Tensorflow, building deep learning models, building a basic neural network using Keras with Tensor Flow, Troubleshoot deep learning models, building deep learning project. (Alog model), Transfer Learning, Inductive, unsupervised Transductive, Deep Learning Tools & Technique
Natural Language Processing & Machine Vision
Understanding Language, NLP Overview, BNF, Grammars, Parsing, Introduction to Language Computing, language models, text classifications, Information retrieval & extraction, Basics for Computational Linguistics, Morphology, Parsing, shallow & deep parsing, semantic interpretation, POS Tagging, chunking, semantic aspects, Pragmatics, Deep Processing for NLP, Statistical Approaches, Methods for NLP, Phonetics, Application domains, MT, IR, Speech, NLG, , Syntactic Analysis, Semantic Analysis, Machine Translation, Information Retrieval, Machine Vision - Human Vision, Image Processing, Interpreting Motion, Face Recognition, Robotics, chat bots.
AI Compute Platforms, Applications & Trends
Hardware as AI compute platform, Parallel Programming models: Parallel Python, Scaling Learning models on HPC platform, Deep learning using HPC/Data Centre/Hadoop, Deployment of Models on distributed platform.AI latest trends and future.
Best Websites for Machine learning Preparation :
1.
Analyticsvidhya
2.
Towardsdatascience
3.
Kaggle for Data