Frequently Asked Questions

• Google Colab
• Python
  1. Matplotlib
  2. Numpy
  3. Pandas
• Basic mathematics
• Basic data visualization
• Data Cleaning/Munging

Overall Goal: Gaining working knowledge in the math required to understand and use data science tools

• Probability Axioms, Random Variables, PDF, PMF, Conditional Probability, Independence, Expectation, Variance
• Describing Common Events using Probability: Bernoulli, Geometric, Binomial, Poisson, Uniform, Normal, Exponential
• Statistical Learning - A/B Testing, Type I and II errors, Sample Size calculation
• Mini project in hypothesis testing

• Introduction to Calculus and Linear Algebra in Data Science
  1. Importance of Calculus and Linear Algebra in Data Science
  2. Basics of Univariate and Multivariate Calculus Vector Operations and Norms
• Deep Dive into Calculus for Data Science
  1. Derivatives and Partial Derivatives
  2. Composite Functions and the Chain Rule
  3. Introduction to Automatic Differentiation
• Optimizing with Gradient Descent and Backpropagation
  1. Gradient Descent Fundamentals
  2. The Mechanics of Backpropagation
• Fundamentals of Linear Algebra
  1. Vector Spaces, Bases, and Dimensions
  2. Linear Transformations and Matrices Matrix Operations in Data Science
• Principal Component Analysis and Matrix Factorization
  1. Principal Component Analysis (PCA): Theory and Application
  2. Overview of Matrix Factorization Techniques (e.g., SVD, QR decomposition)

• Foundations of ML
  1. Problem-solving strategy with data science tools, ML, and DL.
  2. Model selection, feature importance
• Regression Models
  1. Least Squares; Regularization - Elastic Net, Ridge, Lasso; Bias-Variance tradeoff
  2. Development-testing paradigm
• Classification Models
  1. Classification algorithms
  2. Evaluation Metrics: MSE, Accuracy, Precision, Recall, F1 Score
• Decision Trees and Random Forests
  1. Decision Tree Algorithms
  2. Voting Classifiers, Bagging Ensemble models
  3. Random Forests
• Boosting Models
  1. XGBoost
  2. Light GBM
• Unsupervised Learning
  1. Clustering (k-means, dbscan), Agglomerative clustering
  2. Anomaly Detection
• Mini-Project: Five Mini Projects in Machine Learning

• Introduction to Scalable Computing
  1. Overview of scalable computing in AI/ML
  2. Understanding parallel architectures
  3. Importance of scalability in data science
• Introduction to Parallel Computing
  1. Types of parallelism: Data parallelism vs. Task parallelism
  2. Introduction to Shared Memory (OpenMP) and Distributed Memory (MPI)
• Deep Dive into Scalable Computing Technologies
  1. Deep dive into OpenMP and MPI
  2. Introduction to GPUs and Nvidia accelerators
  3. Overview of CUDA programming
• Scalable Data Science Tools
  1. JIT Compiler, Numba, and Dask
  2. Introduction to TensorFlow distributed computing
• Machine Learning at Scale with Parallel ML Libraries
  1. Introduction to Dask, MLLib, cuDF, cuML, cuPY
  2. Focused exploration of Horovod, Ray, and Rapids

• Deep Neural Networks
  1. Multi-Layer Perceptrons (MLP), backprop, Regression/Classification with MLP, gradient issues, and activation functions batch normalization, overfitting, drop out, optimizers and learning rate
• Convolutional Neural Networks
  1. Filtering, Convolution, pooling, Various architectures: U-net, Resnet, etc., classification, localization, segmentation (Computer Vision Applications)
• Recurrent Neural Networks
  1. Sequence modeling, memory cell, GRU, LSTM, gradient issues (NLP Applications)
• Dimensionality Reduction and Self-supervised Neural Networks
  1. PCA, Matrix Completion, LDA, CCA Manifold Learning, t-SNE, LLE
  2. Advanced Auto-encoder type architectures
• Fundamentals of NLP, attention mechanism, and transformer models.
• Mini-Project in Neural Networks

• Introduction to Generative AI
  1. Understanding Generative AI - Introduction to models like GPT, DALL-E, Midjourney, Sora (and others) including their capabilities and limitations.
  2. Exploring the Potential of Generative AI using APIs of large models (e.g., OpenAI).
• Enhancing Applications with Advanced Techniques
  1. Advanced Interaction with Generative Models - Prompt Engineering Techniques and Fine-Tuning
  2. Retrieval-Augmented Generation (RAG)
• Building and Deploying Business Applications
  1. Identifying business problems and architecting solutions incorporating generative models.
  2. Integrating Generative AI into Applications though API integration
  3. Navigating Ethical Implications - Privacy, bias, and copyright issues.

• Introduction to Big Data storage systems
  1. Relational Databases
  2. NoSQL Databases: HBase, Graph DB
  3. Distributed File Systems/HDFS
  4. Cloud storage
• Introduction to Big Data processing platforms
  1. Data Volume: Hadoop, Spark
  2. Data Velocity: Storm, Complex Event Processing
  3. Cloud platforms
• Deep dive into Apache Spark
  1. Resilient Distributed Dataset
  2. Transformations, Actions
  3. Designing computational and analytics applications using Spark
  4. Hands-on with PySpark programming
• Mini-Project in Data Engineering

• Time Series Modeling
  1. Fundamentals, Stationarity, Measures of Dependence
  2. ARMA modeling
• Business Case Studies
  1. Market Basket Analysis (Association Rule Mining)
  2. Optimal Financial Portfolio Allocation
  3. Customer Churn Analysis
• Mini-Project in Business Analytics