Solution by Mansoor Nabawi.
- Linear Regression.
- Distributed Computing with Message Passing Interface (MPI), Exercise 1: Basic Parallel Vector Operations with MPI, Exercise 2: Parallel Matrix Vector multiplication using MPI, Exercise 2: Parallel Matrix Operation using MPI
- Complex Data Lab: Processing Text Data in a Distributed Setting. Exercise 1: Data cleaning and text tokenization. Exercise 2: Calculate Term Frequency (TF). Exercise 3: Calculate Inverse Document Frequency (IDF). Exercise 4: Calculate Term Frequency Inverse Document Fre- quency (TF-IDF) scores (5 points).
- Complex Data Lab: K-means clustering in a Distributed Setting. Distributed K-means Clustering.
- Distributed Machine Learning (Supervised)
- Preparing your Hadoop infrastructure. Setting up a Hadoop infrastructure.
- PyTorch Network Analysis.
- Image Classification, Normalization Effect, Network Regularization, Optimizers (CNN).
- Distributed Computing with Apache Spark.
- Implementing Parallel Stochastic Gradient Descent, PyTorch distributed execution