A day to day plan for this challenge. Covers both theoritical and practical aspects.

I have build Docker Image with all the required dependencies till Day 21. Feel free to use it by pulling it using -> docker pull prakhar21/ml-utilities

Please see Deep Work which compliments our challenge and increases productivity. You can follow me on @Medium for interesting blog articles.

• Learn about Pandas. See Videos(1-5)
• Learn in general about ML See Video (Blackbox Machine Learning)
• Read/Practice Day-1 and Day-2
• See Intro to Linear Regression
• Read LR Docs

• Learn about Pandas. See Videos(6-10)
• Learn in general about ML See Video (Case Study: Churn Prediction)
• Read/Practice Day-3
• See Data Spread
• Andrew Ng See Videos (1-3)

• Learn about Pandas. See Videos(11-15)
• Learn in general about ML See Video (Statistical Learning Theory)
• Read/Practice Day-4 and Day-8
• Visualization in Python See Official Docs

• Learn about Pandas. See Videos(16-18)
• Read KNN-1
• Read KNN-2

• Learn about Pandas. See Videos(19-22)
• Read/Practice Day-7
• General read on Medium

• Learn about Pandas. See Videos(23-26)
• Implementing KNN
• Read/Practice Day-12
• KNN-Sklearn See Official Docs

• Learn about Numpy. Read this
• Naive Bayes - 1
• Naive Bayes - 2
• Naive Bayes - 3
• Naive Bayes - 4

• Lime
• Building Trust in ML models
• Interpretable ML models
• Implementing Naive Bayes
• Learn in general about ML See Video (Stochastic Gradient Descent) - 10 mins onwards

• Lime hands-on news dataset
• Light read about Averaging Ensemble Techniques for more accurate predictions.
• Light reading on Ensemble Techniques
• Implementing Support Vector Machines
• See Ensemble learners

• Implement Average Voting Ensemble Meta Model
• Read about Stacking Ensemble Technique
• Read Stacking from scratch
• Read Stacking-concept-pictures-code

• Read/Practice Day-25
• Read about Feature Scaling
• Read Why, How and When to Scale
• Implementation of Feature scaling techniques
• See Decision Trees - MMDS
• Glance through Decision Trees - Coursera

• Implementing of Decision Trees
• See lectures from Coursera - 2nd week and Coursera - 4th week

• Khan Academy Vector's Section
• Light read on Stacking Classifier
• Implementing - Handeling missing values using pandas
• General read on EM for data imputation

• Read about Model Evaluation
• See Khan Academy Linear combinatations & span and Linear Dependence/Independence
• Explore a Helper Lib

• See Khan Academy Subspaces
• Practice Mlxtend
• Read/Practice Day-33 & Day-34

• Light read on Vector Quantization
• Reading about Boosting Algorithms
• See all videos under Ensembling

• Performance Metrics Hands-on
• Khan Academy Vector dot products
• See Metrics Optimization

• General read on Medium
• Read about Text Classification
• Read about scrape method in Pandas
• Read about FastText

• Glance through Sklearn Docs on Feature Selection
• Read Feature Selection - Analytics Vidhya
• See C2W1L4 and C2W1L5
• Implementing Feature Selection Methods

• Explore A fast and simple progress bar
• Casual read on Pandas - Tips/Tricks - 1 and Pandas - Tips/Tricks - 2
• See Day 35
• Implement data resampling techniques

• See all videos under C2W2
• Implement saving/loading of ML models
• Write Dockerfile

• See and follow along Introduction to PyTorch
• Push Dockerfile and update Docker Readme.

• Read Chapter 6 (till 6.1.2) from the book Mining Massive Datasets
• Read/Practice Day-26

• Read Chapter 6 (till 6.1) from the book Mining Massive Datasets

• Read/Practice Day-27 and Day-28

• See 1, 2, 3 videos from Calculus
• See Week-1 (Video by David Silver)

• Read about article on RL 1, 2, 3, 4
• Implement randomised cartpole balancer

• Read paper
• Implement neural network in PyTorch
• PyTorch + TensorBoard
• Update Docker File/Image

• See 4, 5, 6 videos from Calculus
• See 1, 2, 3, 4 videos from Linear Algebra

• Implementing NN from scratch
• See 5, 6 videos from Linear Algebra

• Implement Cartpole using Cross Entropy method

• Read about Q-Learning.
• See 7, 8, 9 videos from Linear Algebra
• See 7, 8 videos from Calculus

• Read/Practice Day 51
• See But what is a Neural Network?
• Read Grammar correction in text usecase

• See How Neural Networks learn
• Read Text Summarization
• See 10, 11 videos from Linear Algebra
• Read Neural Networks, Manifolds, and Topology

• Implement Q-Learning

• Complete Equations/Graphs/Functions
• See 9, 10 videos from Calculus
• See What does Backpropagation really do ?

• See Backpropagation Calculus
• See 1, 2, 3 from Statistics - Khan Academy

• Read 7 in Assignments
• See 4, 5, 6 from Statistics - Khan Academy

• Read about Agglomerative Clustering

• Read about Deep-Q-Networks and understand epsilon-greedy, replay buffer and target network in the same context.
• See 7, 8 from Statistics - Khan Academy

• Read about Spectral Clustering
• See 9, 10, 11, 12 Statistics - Khan Academy
• Complete Finance and Python

• Read Autoencoders Notebook
• Complete Week-1

• See Neural Voice Cloning
• Complete Week-2
• Read Autoencoder in Text

• Read 1-10 pages of A Primer on Neural Network Modelsfor Natural Language Processing

• Read 11-20 pages of A Primer on Neural Network Models for Natural Language Processing

• Read 21-30 pages of A Primer on Neural Network Models for Natural Language Processing

• Read 31-40 pages of A Primer on Neural Network Models for Natural Language Processing

• Read 41-50 pages of A Primer on Neural Network Models for Natural Language Processing

• Read 51-60 pages of A Primer on Neural Network Models for Natural Language Processing

• Read 61-76 pages of A Primer on Neural Network Models for Natural Language Processing