Data Science Summer Camp Program for Students 2020

• 1. INTRODUCTION
  • What is Machine Learning?
  • Difference between Supervised Learning and Unsupervised Learning?
  • Difference between Regression and Classification Models?

  2. Linear and Multiple Regression

  • Relationship between variables: Regression (Linear, Multivariate Linear Regression) in prediction.
  • Hands on Linear and Multiple Regression using a use case.
  • Understanding the summary output of Linear Regression
  • Residual Analysis
  • Identifying significant features, feature reduction using AIC, multi-collinearity check, observing influential points, etc.
  • Hypothesis testing of Regression Model
  • Confidence intervals of Slope
  • R-square and goodness of fit
  • Influential Observation – Leverage
  • Polynomial Regression
  • Categorical Variable in Regression

  3. Logistic Regression

  • Logistic Regression Intuition
  • Understanding Logit Function.
  • Hands-on Python Session on Logistic Regression using business case.
  • Measuring the Evaluation Metrics – Confusion Metrics, Accuracy, Precision, recall and ROC Curve.

  4. Navie Bayes Classifier

  • Review probability distributions, Joint and conditional probabilities
  • Model Assumptions, Probability estimation
  • Required data processing
  • Feature Selection
  • Classifier

  5. Principal Compound Analysis (PCA)

  • Introduction to dimensionality reduction and it’s necessity
  • Background: Eigen values, Eigen vectors, Orthogonality
  • Principal components analysis (PCA)
  • Feature Extraction
  • Advantage and application of Dimensionality reduction.

  6. Decision Tree (Rule – Based)

  • Decision nodes and leaf nodes
  • Variable Selection, Parent and child nodes branching
  • Stopping Criterion
  • Tree pruning and Depth of a tree
  • Overfitting
  • Metrics for decision trees-Gini impurity, Information Gain, Variance Reduction
  • Regression using decision tree
  • Interpretation of a decision tree using If-else
  • Pros and cons of a decision tree
  • Accuracy estimation using cross-validation 

  7. K-Nearest Neighbor (Distance Based Learning)

  • What is KNN and why do we use it?
  • KNN-algorithm and regression
  • Curse of dimensionality and brief introduction to dimension reduction
  • KNN-outlier treatment and anomaly detection
  • Cross-Validation
  • Pros and cons of KNN

  8. Support Vector Machine (Distance Based Learning)

  • Linear learning machines and Kernel space, making kernels and working in feature space
  • Hands on example of SVM classification and regression problems using a business case in Python.

  9. Esemble Methods

  • Introduction to Ensemble
  • Bias and Tradeoff
  • Bagging & boosting and its impact on bias and variance
  • Random forest
  • Gradient Boosting

  Case Studies:

  • Predictive Analytics
  • Banking Use cases – Customer Service prediction,
  • Health care Use cases – Heart Disease, Diabetics
  • Insurance Use cases
  • Telecom Churn Prediction
  • Bike Sharing
  • Air Quality

Clustering

• Different clustering methods
• review of several distance measures
• Iterative distance-based clustering
• Dealing with continuous, categorical values in K-Means
• Constructing a hierarchical cluster, and density-based clustering.
• Test for stability check of clusters
• Hands-on implementation of each of these methods in Python

1. INTRODUCTION

• What is Text Mining?
• Libraries
  • NLTK
• Structured and Unstructured Data
  • Extracting Unstructured text from files and websites

2. Text Preprocessing

• Regular Expressions for Pattern Matching
• Text Normalization
• Text Tokenization
  • Sentence Tokenization
  • Word Tokenization
• Text Segmentation
  • Stemming
  • Lemmatization

3. Natural Language Understanding (NLP Statistical)

• Automatic Tagging
• N-grams Tagging
• Transformation based Tagging
• Bag of Words
• POS Tagging
• TF – IDF
• Cosine Similarity
• Thinking about the math behind text; Properties of words; Vector Space Model
• Named Entity Recognition
• Relation Extraction

4. Text Classification

Case Studies:

• Text Mining
• Sentiment Analysis
• Spam Detection
• Dialogue Prediction

• • 1. Introduction to Neural Networks
    • Introduction to Neural Network
    • Introduction to Perceptron
    • Activation Functions
    • Cost Functions
    • Gradient Decent
    • Stochastic Gradient Descent
    • Back propagation

    2. Deep Frameworks

    • Installing Tensorflow and Keras
    • Tensorflow and Keras Basic Syntax
    • Tensorflow Graphs
    • Variables and Placeholder
    • Saving and Restoring Models
    • Tensorboard

    3. Artificial Neural Network with Tensorflow

    • Neural Network for Regression
    • Neural Network for Classification
    • Evaluating the ANN
    • Improving and tuning the ANN

    4. Convolution Neural Networks

    • Convolution Operation
    • ReLU Layer
    • Pooling
    • Flattening
    • Full Connection
    • Softmax and Cross Entropy

    Case Studies:

    • Image Classification

    5. Keras (Backend Tensorflow)

    • • Keras vs Tensorflow
      • Introduction to Keras
      • Building Artificial Neural Network with Keras
      • Building Convolution Neural Network with Keras

     

Projects

• • • Face Recognition

Face Recognition project gives details of the person and can recognize the gender and names. This project involves in

• • 1. Collection of images
    2. Preprocessing the data
    3. Applying the Model (Machine Learning or Deep Learning)
    4. Training and Testing using the model

Ex: Security Unlock, Gender Recognition, Identity Recognition 

• • • Chatbot

Virtual Assistants are now a common requirement for an Organization. But, to make the assistant more effective we are now into the chatbots which involves Natural Language Process, Deep Learning and Artificial Intelligence. This interactive chatbots are designed to serve as an intellectual responsive process.

 Ex: Alexa, Siri, Google Assistant

• Creating pickle and frozen files
• Cloud Deploying Machine Learning and Deep Learning model for production