- Optimization in NNs: [CS231n-opt1] [CS231n-opt2] [Opt-Algos]
- Basics and NNs: [CS231n-classify-1] [CS231n-classify-2] [CS231n-nn1] [CS231n-nn2] [CS231n-nn3] [L1/L2-explained] [Dropout-explained]
- Batch Normalization: [Backward pass using graph] [Backward pass with derivatives] [Video: BN-Training] [Video: BN-Testing]
- Decision Trees/Random Forests: [ISLR Chap-8]
- Principal Component Analysis(PCA): [PCA Tutorial] [ISLR 10.2] [PCA-2]
- Clustering: [ISLR Chap-10] [k-means] [Clustering-CMU] [kNNs: Pros/Cons]
- ICA/FA: [ICA] [FA]
- Classification: [[ISLR-Chap4]] [LR/NB]
- Regression: [[ISLR-Chap3]]
- Boosting: [Adaboost] [Gradient Boosting-1] [Gradient Boosting-2] [LightGBM/XGBoost] [GBM regression] [GB-2]
- SVM: [Very Detailed Tutorial from Microsoft]
- EM: [EM]
- Bootstrap: [Bootstrapping in R]
- Supplemental Readings: [KDNuggets:10 statistical techniques]
- Multi-variate Gaussians: [Gaussians-1] [Gaussians-2]
- Sampling: [CDF-INV] [Box-Mueller/Marsaglia-Polar] [Detailed Maths] [Gaussian-Inv,BM] [Sampling uniformly on sphere]
- Sample Mean/variances of Gaussian: [Distribution of sample variance]
- Hypothesis Testing: [Summary]https://www.csus.edu/indiv/j/jgehrman/courses/stat50/hypthesistests/9hyptest.htm
- A/B Testing: [1] [2] [3] [4] [5] [6] [A/B w/ Python] [2]
- Martingale: [1] [2] [3] [4]
- Supplemental Readings: [Cantor’s Diagonalization argument]
- CNNs: [Basics] [Visualizing CNNs] [Fine-tuning CNNs] [CNN Backprop/Architectures Chap8]
- NLP: [Word Embeddings/Word2Vec] [LSTM-1] [LSTM-2] [LSTM-3]
- DQN: [Understanding Deep-Q Networks] [Understanding PER] [Rainbow is all you need]
- Frameworks: [Tensorflow/Pytorch brushup]
- Python call by value or reference? [1] [2] [3] [4]
- How does Python work? Interpreter vs Compiler? [1] [2]
- Memory Management in Python: [1]
- Dictionaries Implementation in Python: [1]
- OOP in Python: [1]
- ML System Design: [Consolidated resource from chiphuyen] [Facebook's ML system series] [Leetcode Discuss]
- System Design: [1]
- Supplementary Readings: [A Recipe for Training Neural Networks]
- All of Statistics by Larry Wasserman: [Book] [Course Q/A] [Book sols]
- Comprehensive ML Book from Berkley CS189 Course: [1] [2] [3]
- [What Every Computer Scientist Should Know About Floating-Point Arithmetic]
- [Feature Engineering] [Data Cleaning]
- [Learning to Rank]
- [Math 4 ML Book]
- Exams/Assignments of ML courses w/ solutions: https://tbp.berkeley.edu/courses/cs/189/
- Basic DS and Algo in Python [Online Book]
- Leetcode problems
Resources:
- CMU Spring'16 by Tom Mitchell and Nina [Course Link]
- An Introduction to Statistical Learning [Book]
- Pre-requisites: [Matrix Derivatives] [Derivatives Cheatsheet]
- CS229 Review Notes (Pre-reqs): [Probability] [Linear Algebra] [Convex Optimization-1] [2] [Gaussians-1] [Gaussians-2] [Gaussian Processes]
- CS229 Review Notes: [Backprop] [DL] [Decision Trees] [Ensemble Methods] [Linear Regression and Classification (Supervised)] [Generative Learning] [SVM] [Learning Theory] [Regularization and Model Selection] [Perceptron] [k-means] [GMMs] [EM] [ [RL] [LQR, DDP and LQG] [Boosting] [HMM Notes] [Evaluation Metrics]
- Other topics: [Anomaly Detection] (find better link?)
- Topics:
Resources:
- CS231 Assignment Soln Ref: [ref-tf-1] [ref-pytorch-1] [ref-3] [ref-4]
- Basics/Losses: [Image Classification] [Linear Classification]
- Backprop: [Optimization-1] [Optimization-2] [Optimizing GD] [Appendix1:Linear Example] [Appendix2:Derivatives] [Appendix3:Vector Derivatives]
- NNs: [NN-1] [NN-2] [NN-3] [NN-case study]
- RNNs and LSTMs: [LSTMs]
- NLP: [Word Vectors-I] [Word Vectors-II] [NNs] [RNN/LSTM-1] [Neural Machine Translation, Seq2Seq, Attention]
- RL: [Basics: David Silver Course Deep RL - DQN and variants: [1] [2] [3-PER] [RL-Hard]
ToDO: Add (i)Other networks like BiGRU etc-- find a summary article, (ii) VAEs/GANs, (iii) Word2VEc, and word representations, (iv) implementation of basic models of MNIST/CIFAR-10 models using python for NNs and CNNs, char-rnn models for LSTM, RL playing game model, (v) batch norm
unsorted links:
- charrnn: http://karpathy.github.io/2015/05/21/rnn-effectiveness/
- https://deepgenerativemodels.github.io/notes/vae/
- MS_Sharma links
- Really great Stats/ML: http://www.stat.cmu.edu/~cshalizi/uADA/12/
- Data Scientist Interview links: https://github.com/ml874/Cracking-the-Data-Science-Interview
- https://sebastianraschka.com/faq/docs/
Resources:
- Quantitative Finance Interview Question Bank: [Green Book] Chapter 4, 5.1-5.3, 3.6, 7, 2
- Probability and Statistics: Introduction to Probability by Bertsekas [Book] [Lecture Notes] [Summary Notes] [Solutions]
- Linear Algebra (not final): [Review] [Slides] [Notes] [Comprehensive Book]
- Convex Optimization (Not doing): [Notes-1] [Notes-2] [Comprehensive Book]
Resources:
- Linear Algebra etc.
DS/Algorithms: Recursion, DP, Strings, ... Statistics in Python: [Short-pyStats] [Long-pystats] [Coursera]