Introduction to Python
Python Basics, Python Functions and Packages, Working with Data Structures, Arrays, Vectors & Data Frames, Jupyter Notebook – Installation, & function, Pandas, NumPy, Matplotlib, Seaborn.
EDA and Data Processing
Data Types, Dispersion & Skewness, Uni & multi Variate Analysis, Data imputation, Identifying and normalizing, Outliers
Applied Statistics
Descriptive Statistics, Probability & Conditional Probability, Hypothesis Testing, Inferential Statistics, Probability Distributions
Supervised learning
Linear Regression, Multiple Variable Linear, Regression, Logistic Regression, Naive Bayes Classifiers, k-NN Classification, Support Vector Machinesr
Ensemble Techniques
Decision Trees, Bagging, Random Forests, Boosting
Unsupervised learning
K-means Clustering, Hierarchical Clustering, Dimension Reduction-PCA
Featurisation, Model Selection & Tuning
Feature engineering, Model selection and tuning, Model performance measures, Regularising Linear models, ML pipeline, Bootstrap sampling, Grid search CV, Randomized search CV, K fold cross-validation
Recommendation Systems
Introduction to Recommendation Systems, Popularity based model, Content based Recommendation System, Collaborative Filtering (User similarity & Item similarity), Hybrid Models
Time-series Forecasting
Introduction to forecasting data, Properties of Time Series data, Examples and features of Time Series data, Naive, Average and Moving Average Forecasting, Exponential Smoothing, ARIMA Approach
Model deployment
Model serialization- pickle and joblib, Rest APIs- Flask (real-time prediction), Docker Containerization, Kubernetes (using Google cloud)
Introduction to Neural Networks and Deep Learning
Introduction to Perceptron & Neural Networks, Activation and Loss functions, Gradient Descent, Batch Normalization, TensorFlow & Keras for Neural Networks, Hyper Parameter Tuning
Computer Vision
Introduction to Convolutional, Neural Networks, Introduction to images, Convolution, Pooling, Padding & its mechanisms, Forward Propagation & Backpropagation for CNNs, CNN architectures like AlexNet, VGGNet, InceptionNet & ResNet, Transfer Learning, Object Detection, YOLO, R-CNN, SSD, Semantic Segmentation, U-Net, Face Recognition using Siamese Networks, Instance Segmentation
NLP (Natural Language Processing)
Introduction to NLP, Stop Words, Tokenization, Stemming and lemmatization, Bag of Words Model, Word Vectorizer, TF-IDF, POS Tagging, Named Entity Recognition, Introduction to Sequential data, RNNs and its mechanisms, Vanishing & Exploding gradients in RNNs, LSTMs - Long short-term memory, GRUs - Gated recurrent unit, LSTMs Applications, Time series analysis, LSTMs with attention mechanism, Neural Machine Translation, Advanced Language Models: Transformers, BERT, XLNet
Introduction to Reinforcement Learning (RL)
RL Framework, Component of RL Framework, Examples of RL Systems, Types of RL Systems, Q-learning
Introduction to GANs (Generative adversarial networks)
Introduction to GANs, Generative Networks, Adversarial Networks, How GANs work?, DCGANs - Deep Convolution GANs, Applications of GANs
PROJECTS
To identify the potential customers who have a higher probability to churn using ensemble prediction model
To cluster the vehicles as per their fuel consumption attributes and later train a regression model for an automobile dataset
To create an automation using computer vision to impute dynamic bounding boxes to locate cars or vehicles on the road
Implementing an Image classification neural network to classify Street House View Numbers
Predicting the condition of the patient depending on the received test results
To build a NLP classifier which can use input text parameters to determine the label/s of the blog
To build a recommendation system using popularity based and collaborative filtering methods to recommend mobile phones to a user which are most popular and personalised respectively
Sarcasm Detection using Bidirectional LSTMs
To build a semi-rule based text chat bot which can give static responses to the user depending on the inputs for industrial safety and incidents
To build an image classifier and object detection model which can classify a car from an image and identify the location of the car from an image by publishing a bounding box around it
To build an image classifier and object detection model which can classify an chest X-ray image into with/without pneumonia disease and identify the location of the chest X-ray where the disease is localised by publishing a bounding box around it
To build an image classifier which can classify images of dogs as per their breeds