AI & Machine Learning

In this new era, innovative technology is the driving force and Artificial Intelligence or AI is at the centre of it.

Artificial Intelligence is bringing a revolutionary change in business models, various processes, and customer relationships across every industry globally. In this new era, organizations need to skilfully integrate AI into their overall strategy to reach the zenith of success.

Advanced Diploma - Artificial Intelligence and Machine Learning is a one-year Diploma program that provides in-depth knowledge of the fundamentals of Artificial Intelligence, programming, and Machine Learning through an array of special modules. Machine Learning builds a model based on sample data, known as training data to make predictions to detect and analyse trends, solve problems and answer business-related questions. Machine Learning is an effective data analysis method for business and other fields that works by automating the process of building data models.

This new Advanced Diploma Programme is a perfect blend of cutting-edge academic learning with knowledge about the impact of Artificial Intelligence. Through this program, you will learn how to skilfully develop, implement and run AI systems.

In order to take up the Artificial Intelligence & Machine Learning course, the minimum student qualification is 10+2

Minimum: One academic year as two semesters from the year of joining the course
Maximum Duration for the completion of the course: The Candidate shall have to complete the course within two academic years from the year of joining the course

Preferred English (Can be English Hindi Mixed)
Mode of Study and Examination: Hybrid Mode (Online and Off-line both)

S.N.	Subjects	Credit
1	Mathematics Essential	4
2	Data Science and Basic SQL	4
3	Basic Statistics and Probability	4
4	Programming in Python	6
5	Programming in Python - LAB	4
6	Exploratory Data Analysis - EDA	2
7	Introduction to Artificial Intelligence	2
8	Internship	2
	Total:	28

S.N.	Subjects	Credit
1	Data Science Applications of NLP	4
2	Data Visualization	4
3	Machine Learning	4
4	Game Theory and Artificial Intelligence	4
5	Distributed Systems and Cloud Computing	4
6	Deep Learning	2
7	Distributed Systems and Cloud Computing - LAB	2
8	Capstone Project Work	4
	Total:	28

S.N.	Semester	Duration	Start Date	End Date	Total Hours
1	First	3 months	01-01-2023	31-03-2023	240 Hrs
2	Internship	2 months	01-04-2023	31-05-2023	60 Hrs
3	Second	3 months	01-06-2023	30-09-2023	240 Hrs
4	Capstone Project	2 months	01-10-2023	30-11-2023	60 Hrs
5	Final Exam	15 Days	10-12-2023	31-12-2023

1. Foundation of Python:

• Keywords and identifiers, comments, indentation and statements, Variables and data types in Python, Standard Input and Output,
• Operators Control flow: if else, if...elf...else, if statement.
• Control flow: for loop, while loop, break and continue
• List, Tuple, Dictionary, Sets, Strings.
• Functions: Types of functions, Function arguments, Recursive functions, Lambda functions, Time and Space complexity.

2. Foundation of SQL:

• Introduction to Databases, Why SQL? Execution of an SQL statement, Installing MySQL.
• DESCRIBE, SHOW TABLES, SELECT, LIMIT, OFFSET, ORDER BY, DISTINCT, WHERE, Comparison operators, NULL, Logical Operators
• Aggregate Functions: COUNT, MIN, MAX, AVG, SUM, GROUP BY, HAVING, Order of keywords.
• Joins: Join and Natural Join, Inner, Left, Right and Outer joins. Sub Queries/Nested Queries/ Inner Queries,
• DML: INSERT, UPDATE, DELETE, And DDL: CREATE TABLE, DDL: ALTER: ADD, MODIFY, DROP, DDL: DROP TABLE, TRUNCATE, DELETE
• Data Control Language: GRANT, REVOKE

3. Foundation of Numpy:

• Getting Into Shape: Array Shapes and Axes, Mastering Shape, Understanding Axes, Broadcasting
• Data Science Operations: Filter, Order, Aggregate, Indexing, Masking and Filtering, Transposing, Sorting, and Concatenating, Aggregating
• Numerical Types: int, bool, float, and complex

4. Foundation of Pandas:

• How does pandas fit into the data science toolkit?
• When should you start using pandas?
• Install and import pandas
• Core components of pandas: Series and DataFrames - Creating DataFrames from scratch
• Reading data from CSVs, Excel, html, Json, etc.
• Reading data from a SQL database.
• Converting back to a CSV, JSON, or SQL.
• DataFrame operations: Viewing your data- head/tail
• Getting info & description about your data.
• Handling duplicates, Column clean up - df.columns, rename of columns.
• How to work with missing values. Removing null values
• Imputation, DataFrame slicing, selecting, extracting
• Conditional selections.
• Applying functions

5. Foundation of Matplotlib & Seaborn:

• Scatter Plot.
• Line Plot.
• Bar Graph.
• Histogram.
• Box plot, Violin Plot, Contour Plot.

6. Exploratory Data Analysis (EDA):

• Univariant Analysis: 1D Scatter plot, PDF, CDF, Histogram, Mean, Variance, Standard Deviation, Median, Percentiles and Quantiles, IQR (Inter Quartile Range) and MAD (Median Absolute Deviation), Box-plot with Whiskers, Violin Plots.
• Bivariant Analysis: 2D Scatter plot
• Multivariant Analysis: Pair plot
• Multivariate Probability Density, Contour Plot

7. Dimensionality Reduction & Visualization:

• What is Dimensionality reduction? Row Vector and Column Vector, How to represent a dataset as a matrix. Data Pre-processing: Feature Normalisation, Column Standardization, Co- variance of a Data Matrix, MNIST dataset (784 dimensional), Code to Load MNIST Data Set, Revision Dimensionality Reduction and Visualization.
• Why learn PCA? Geometric intuition of PCA, Mathematical objective function of PCA, Alternative formulation of PCA: Distance minimization, Eigen values and Eigen vectors (PCA): Dimensionality reduction
• PCA for Dimensionality Reduction and Visualization, Visualize MNIST dataset, Limitations of PCA, PCA Code example, PCA for dimensionality reduction (not-visualization),Revision Principal Component Analysis
• What is t-SNE? Neighbourhood of a point, Embedding, Geometric intuition of t-SNE, Crowding Problem, How to apply t- SNE and interpret its output, t-SNE on MNIST, Code example of t-SNE.

8. Linear Algebra:

• Why learn it ?, Introduction to Vectors(2-D, 3-D, n-D) , Row Vector and Column Vector, Dot Product and Angle between 2 Vectors, Projection and Unit Vector, Equation of a line (2-D), Plane(3-D) and Hyper plane (n-D), Plane Passing through origin, Normal to a Plane, Distance of a point from a Plane/Hyper plane, Half- Spaces, Equation of a Circle (2-D), Sphere (3-D) and Hyper sphere (n-D), Equation of an Ellipse (2-D), Ellipsoid (3-D) and Hyper ellipsoid (n- D), Square ,Rectangle, Hyper Cube, Hyper Cuboid.

9. Probability and Statistics:

• Introduction to Probability and Statistics, Population and Sample, Gaussian/ Normal Distribution and its PDF(Probability Density Function), CDF(Cumulative Distribution function) of Gaussian/Normal distribution, Symmetric distribution, Skewness and Kurtosis, Standard normal variate (Z) and standardization, Kernel density estimation, Sampling distribution & Central Limit theorem
• Q-Q plot: How to test if a random variable is normally distributed or not?, How distributions are used?, Chebyshev's inequality, Discrete and Continuous Uniform distributions, How to randomly sample data points (Uniform Distribution), Bernoulli and Binomial Distribution, Log Normal Distribution, Power law distribution, Box cox transform
• Applications of non-Gaussian distributions? Co-variance, Pearson Correlation Coefficient, Spearman Rank Correlation Coe?icient, Correlation vs Causation, How to use correlations? , Confidence interval (C.I) Introduction, Computing confidence interval given the underlying distribution, C.I for mean of a normal random variable, Confidence interval using bootstrapping.
• Hypothesis testing methodology, Null- hypothesis, p-value, Hypothesis Testing Intuition with coin toss example, Resampling and permutation test, K-S Test for similarity of two distributions
• Hypothesis testing: What is hypothesis testing, How to use hypothesis testing?

10. Foundations of Natural Language Processing and Machine Learning:

• Bi-Grams and n-grams (Code Sample), TF-IDF (Code Sample), Implementing TFIDF vectorizer, Word2Vec (Code Sample), Avg-Word2Vec and TFIDF- Word2Vec
• How "Classificatio" works?
• How "Regression" works?
• Getting Started With Python's NLTK
• Tokenizing
• Filtering Stop Words
• Stemming
• Tagging Parts of Speech
• Lemmatizing
• Chunking
• Chinking
• Using Named Entity Recognition (NER)

11. Classification & Regression model: K-Nearest Neighbours

• How "Classification" works? Data matrix notation, Classification vs Regression (examples), K- Nearest Neighbours Geometric intuition with a toy example, Failure cases of KNN, Distance measures: Euclidean(L2), Manhattan(L1), Murkowski, Hamming.
• Cosine Distance & Cosine Similarity, How to measure the effectiveness of k-NN? Test/Evaluation time and space complexity, KNN Limitations, Decision surface for K-NN as K changes.
• Overfitting and Underfitting, Need for Cross validation, K- fold cross validation, Visualizing train, validation and test datasets.
• How to determine overfitting and underfitting?, Time based splitting, k-NN for regression, Weighted k-NN, Voronoi diagram, Binary search tree, How to build a kd-tree, Find nearest neighbours using kd-tree, Limitations of Kd tree, Extensions, Hashing vs LSH, LSH for cosine similarity, LSH for euclidean distance, Probabilistic class label, Code Sample:Decision boundary.
• Code Sample: Cross Validation, Assignment: Implement RandomSearchCV with k fold cross validation on KNN.

12. Classification Algorithms in various situations:

• Introduction, Imbalanced vs balanced dataset, Multi-class classification, k-NN, given a distance or similarity matrix, Train and test set differences.
• Impact of outliers, Local outlier Factor (Simple solution :Mean distance to Knn), K-Distance(A),N(A), Reachability-Distance(A,B), Local reachability- density(A), Local outlier Factor(A), Impact of Scale & Column standardization, Interpretability, Feature Importance and Forward Feature selection, Handling categorical and numerical features.
• Handling missing values by imputation, Curse of dimensionality, Bias-Variance tradeoff, Intuitive understanding of bias- variance. Best and worst cases for an algorithm.

13. Performance Measurement of Models:

• Accuracy, Confusion matrix, TPR, FPR, FNR, TNR, Precision and recall, F1- score, Receiver Operating Characteristic Curve (ROC) curve and AUC, Log-loss, R-Squared/ Coefficient of determination, Median absolute deviation (MAD), Distribution of errors, Assignment: Compute Performance metrics without Sklearn

14. Naive Bayes:

• Conditional probability, Independent vs Mutually exclusive events, Bayes Theorem with examples, Exercise problems on Bayes Theorem.
• Naive Bayes algorithm, Toy example: Train and test stages, Naive Bayes on Text data.
• Laplace/Additive Smoothing, Log-probabilities for numerical stability, Bias and Variance tradeoff, Feature importance and interpretability, Imbalanced data, Outliers, Missing values, Handling Numerical features (Gaussian NB), Multiclass classification, Similarity or Distance matrix, Large dimensionality, Best and worst cases, Multinomial Naive Bayes.
• Getting Text to Analyse
• Using a Concordance
• Making a Dispersion Plot
• Making a Frequency Distribution
• Finding Collocations

15. Logistic Regression:

• Mathematical formulation of Objective function, Weight vector, L2 Regularization: Overfitting and Underfitting.
• L1 regularization and sparsity, Probabilistic Interpretation: Gaussian Naive Bayes, Loss minimization interpretation, Hyperparameter search: Grid Search and Random Search CV.
• Column Standardization, Feature importance and Model interpretability, Collinearity of features, Test/ Run time space and time complexity, Real world cases, Non-linearly separable data & feature engineering.
• Code sample: Logistic regression, GridSearchCV, RandomSearchCV, Extensions to Logistic Regression: Generalized linear models.

16. Linear Regression:

• Geometric intuition of Linear Regression, Mathematical formulation, and Real world Cases, Code sample for Linear Regression, Question and Answers, Revision Linear Regression.

17. Solving Optimization Problem:

• Differentiation, Online differentiation tools, Maxima and Minima, Vector calculus: Grad, Gradient descent: geometric intuition.
• Learning rate, Gradient descent for linear regression, SGD algorithm, Constrained Optimization & PCA, Logistic regression formulation revisited, Why L1 regularization creates sparsity?
• Assignment: Implement SGD Classifier with Log Loss and L2 regularization Using SGD: without using sklearn.

18. Support Vector Machine (SVM):

• Geometric Intuition, Why we take values +1 and -1 for Support vector planes, Mathematical derivation.
• Loss function (Hinge Loss) based interpretation, Dual form of SVM formulation, Kernel trick, Polynomial kernel, RBF-Kernel, Domain specific Kernels, Train and run time complexities, nu- SVM: control errors and support vectors, SVM Regression, Cases, Code Sample.

19. Decision Tree:

• Geometric Intuition of decision tree: Axis parallel hyper planes, Sample Decision tree, Building a decision Tree: Entropy,
• Building a decision Tree: Information Gain, Building a decision Tree: Gini Impurity
• Building a decision Tree: Constructing a DT, Building a decision Tree: Splitting numerical features, Feature standardization, Building a decision Tree: Categorical features with many possible values, Overfitting and under fitting, Train and Run time complexity, Regression using Decision Trees.
• Code Sample of Decision Tree.

20. Ensemble Models:

• What are ensembles? Bootstrapped Aggregation (Bagging) Intuition, Random Forest and their construction, Bias-Variance tradeoff, Bagging :Train and Run-time Complexity., Bagging: Code Sample, Extremely randomized trees.
• Random Tree: Cases, Boosting Intuition, Residuals, Loss functions and gradients, Gradient Boosting, Regularization by Shrinkage, Train and Run time complexity, XGBoost: Boosting + Randomization, AdaBoost: geometric intuition, stacking models, cascading classifiers.
• Application & Code of GBDT/XGBOOST/LIGHT-GBM

21. Data Mining (Unsupervised Learning) - Clustering:

• What is Clustering? Unsupervised learning, Applications, Metrics for Clustering, K-Means: Geometric intuition, Centroids, K-Means: Mathematical formulation: Objective function.

22. K-Mean Clustering:

• K-Means Algorithm. How to initialize: K-Means++, Failure cases/Limitations, K- Medoids.
• Determining the right K, Code Samples, Time and space complexity.

23. Hierarchical Clustering:

• Agglomerative & Divisive, Dendrograms, Agglomerative Clustering, Proximity methods: Advantages and Limitations. Time and Space Complexity, Limitations of Hierarchical Clustering, Code sample.

24. Density based clustering:

• Density based clustering, MinPts and Eps: Density, Core, Border and Noise points, Density edge and Density connected points., DBSCAN Algorithm, Hyper Parameters: MinPts and Eps, Advantages and Limitations of DBSCAN, Time and Space Complexity, Code samples. Neural Networks, Computer Vision and Deep Learning:

25. Neural Network:

• History of Neural networks and Deep Learning., How Biological Neurons work? Growth of biological neural networks, Diagrammatic representation: Logistic Regression and Perceptron.
• Multi-Layered Perceptron (MLP). Notation, Training a single-neuron model., Training an MLP: Chain Rule.
• Training an MLP: Memoization, Backpropagation. Activation functions, Vanishing Gradient problem., Bias-Variance tradeoff.

26. Deep Multi-Layer Perceptron's:

• Deep Multi-layer perceptrons: 1980s to 2010s, Dropout layers & Regularization. Rectified Linear Units (ReLU).
• Weight initialization. Batch Normalization., Optimizers: Hill-descent analogy in 2D.
• Optimizers: Hill descent in 3D and contours. SGD Recap, Batch SGD with momentum. Nesterov Accelerated Gradient (NAG).
• Optimizers: AdaGrad, Optimizers: Adadelta and RMSProp, Adam, Which algorithm to choose when? Gradient Checking and clipping, Softmax and Cross- entropy for multi-class classification.
• How to train a Deep MLP? Auto Encoders., Word2Vec : CBOW, Word2Vec: Skip- gram, Word2Vec : Algorithmic Optimizations.

27. Tensor flow & Keras:

• Tensorflow and Keras overview, GPU vs CPU for Deep Learning., Google Colaboratory., Install TensorFlow, Online documentation and tutorials.
• Softmax Classifier on MNIST dataset., MLP: Initialization, Model 1: Sigmoid activation.
• Model 2: ReLU activation., Model 3: Batch Normalization., Model 4 : Dropout., MNIST classification in Keras., Hyperparameter tuning in Keras.
• Exercise: Try different MLP architectures on MNIST dataset. Revision Tensorflow And Keras.

28. Convolutional Neural Nets (CNN):

• Biological inspiration: Visual Cortex, Convolution: Edge Detection on Images. Convolution: Padding and strides.
• Convolution over RGB images. Convolutional layer., Max-pooling., CNN Training: Optimization, Example CNN: LeNet [1998], ImageNet dataset., Data Augmentation., Convolution Layers in Keras.
• AlexNet, VGGNet, Residual Network., Inception Network., What is Transfer learning., Code example: Cats vs Dogs. Code Example: MNIST dataset.
• Transfer Learning.

29. Long Short-Term Memory (LSTMS):

• Why RNNs? , Recurrent Neural Network. Training RNNs: Backprop.
• Types of RNNs. Need for LSTM/GRU., LSTM. GRUs.
• Deep RNN., Bidirectional RNN., Code example: IMDB Sentiment classification, Assignment: LSTM on Donors Choose - (LSTM with Text and categorical data)
• Sample code.

30. Generative Adversarial Networks (GANs):

• Deep Learning: Generative Adversarial Networks (GANs): Live session on Generative Adversarial Networks (GAN)
• Encoder- Decoder Models
• Attention Models in Deep Learning: Attention Models in Deep Learning

31. BERT-Transformer:

• Deep Learning: Transformers and BERT: Transformers and BERT.