One Stop for machine learning
Sections:
- Papers
- Languages
- Platforms
- Courses
- Live Sessions
- Books
- Cheat sheets
- Interview Questions
- DataSets
- Blogs and Community
- Online Competitions
- Other Sources
- About CNNs
- About GANs
Steps in approaching a Machine learning problem:
Below are the steps that I follow while approaching a ML problem.
- Defining and understanding the problem statement
- Gathering the Data
- Initial Exploration of Data
- In-depth EDA
- Building the model
- Analyzing the results with different models and shortlisting the ones which gives good performance measures
- Fine-tuning the selected model
- Document the code
- Deployment
- Monitoring the deployed model performance in real time.
Papers | 2020
- Towards a Human-like Open-Domain Chatbot
- ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
- Reformer: The Efficient Transformer
- Longformer: The Long-Document Transformer
- You Impress Me: Dialogue Generation via Mutual Persona Perception
- Recipes for building an open-domain chatbot
- ToD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogues
- SOLOIST: Few-shot Task-Oriented Dialog with A Single Pre-trained Auto-regressive Model
- A Simple Language Model for Task-Oriented Dialogue
- FastBERT: a Self-distilling BERT with Adaptive Inference Time
- PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector Elimination
- Data Augmentation using Pre-trained Transformer Models
- FLAT: Chinese NER Using Flat-Lattice Transformer
- End-to-End Object Detection with Transformers | code
- Objects as Points | code
- Acquisition of Localization Confidence for Accurate Object Detection | code
- Part-A^2 Net: 3D Part-Aware and Aggregation Neural Network for Object Detection from Point Cloud
- PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud | code
- LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving
- Probabilistic 3D Multi-Object Tracking for Autonomous Driving | code
- A Baseline for 3D Multi-Object Tracking | code
- Denoising Diffusion Probabilistic Models | code
- Joint Training of Variational Auto-Encoder and Latent Energy-Based Model
- Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors | code
- BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning | code
- Stable Neural Flows
- How Good is the Bayes Posterior in Deep Neural Networks Really
Languages
Knowing one language couldn't help to work in multidomain,so its good to learn two or more languages like python, c++, java. For machine learning,one should be sound in any of the language with other language basics python, R, matlab, julia.
- Jet Brains
Jet Brains provides basics to advance training onJava,KoltinandPythonlanguages, can learn and apply in developing mini projects based on the level selected. - HackerRank
- HackerEarth
- LeetCode
- CodeChef
- CP algorithms
Platforms
As we know that machine(deep) learning models need high computational power, it might not be possible for an individual for purchase addtional CPUs or GPUs, so we use cloud platforms.
Note: In general we use Jupyter Notebook to run our models. For Jupyter Notebook we need to install the software on local machine, for windows, linux
Note: Google Products like Colab, Kaggle are free and best platform for an individual.
Courses
Most of the courses are available in Python language. kindly re-check before taking the course of you have any language constraints.
Note: No organisation can be seen here, kindly pick the course based on your requirement.
Machine Learning
- Machine Learning (Stanford CS229)
- Python for Machine Learning (Great Learning)
- Statistics for Machine Learrning (Great Learning)
- Data Visualization using Python (Great Learning)
- Machine Learning Crash Course (Google)
- Machine Learning - Linear Regression (LEAPS)
- Getting started with Decision Trees (Analytics Vidhya)
- Machine Learning with Python: A Practical Introduction (Harvard EdX)
- Machine Learning Fundamentals (Harvard EdX)
- Machine Learning with Python: from Linear Models to Deep Learning (Harvard EdX)
- Machine Learning (Harvard EdX)
- Machine Learning with Python (IBM)
- Machine Learning – Dimensionality Reduction (IBM)
- Data Visualization with Python (IBM)
- Data Analysis with Python (IBM)
- Applied Machine Learning 2020 (Columbia)
DataScience
- Introduction to Python (Analytics Vidhya)
- Fundamentals of Data Analytics (LEAPS)
- Pandas for Data Analysis in Python (Analytics Vidhya)
- Tableau for Beginners (Analytics Vidhya)
- Top Data Science Projects for Analysts and Data Scientists (Analytics Vidhya)
- Machine Learning for Data Science and Analytics (Harvard EdX)
- A data science program for everyone (Harvard EdX)
- Data Science and Machine Learning Capstone Project (Harvard EdX)
- R Basics (Harvard EdX)
- Data Visualisation and EDA (Harvard EdX)
- Probability Theory (Harvard EdX)
- Data Science Inference and Modeling (Harvard EdX)
- Data Science Productivity Tools (Harvard EdX)
- Data Science Wrangling (Harvard EdX)
- Data Science Linear Regression (Harvard EdX)
- Capstone Project (Harvard EdX)
- Introduction to Data Science (IBM)
- Python for Data Science (IBM)
- SQL and Relational Databases 101 (IBM)
APIs
- Deep Learning Fundamentals (IBM)
- Deep Learning with TensorFlow (IBM)
- Accelerating Deep Learning with GPU (IBM)
- Convolutional Neural Networks for Visual Recognition (Stanford CS231n)
Artificial Intelligence
- Introduction to Artificial Intelligence with Python (Harvard EdX)
- Introduction to Artificial Intelligence (UC Berkeley CS188)
Natural Language Processing
- Introduction to Natural Language Processing
- Natural Language Processing (NLP) - Microsoft
- Natural Language Processing with Deep Learning (Stanford CS224N)
- Natural Language Understanding (Stanford CS224U)
Commputer Vision
Matlab
Live Sessions
Note: In the below available sections if the required book/cheatsheet is not present or for more info check the more .
Note: Few google links are getting crashing for few files, in such scenario, can direclty check more (folder) .
EBooks/Books/CookBooks
- What is Machine Learning
- Tree Based Algorithms
- Natural Language Processing
- Data Cleaning with Numpy and Pandas
- Data Engineering CookBook
- Machine Learning Projects in Python (Compiled)
- Natural Langugae with Python
Cheat Sheets
- Python
- R
- SQL
- Machine Learning
- Supervised learning
- Data Science
- Probability
- Statistics
- Data Engineering
- Git
Exercises
Interview Questions
- Python
- Data Science
- Variance in Data Science
- Interview question data science
- Self prepared Interview Questions
Note: These Self prepared Interview Questions will be updated weekly.
DataSets
- Kaggle
- Meta-Sim: Learning to Generate Synthetic Datasets
- UCI
- Worldbank Data
- Tensorflow
- Movielens
- Huggingface
Blogs and Community
- Towards data science
- Analyticsvidhya
- Machinelearningmastery
- Medium
- PyTorch Discussion Forum
- StackOverflow PyTorch Tags
- Website
Online Competitions
Other Resources
- Paperswithcode
- Google research
- Madewithml
- Deeplearning
- Huggingface
- Arcgis
- Pytorchdeeplearning
- Fastaibook
- EasyOCR
- Awesome Data Science
- NLP progress
- Recommenders
- Awesome pytorch list
- Free data science books
- Deeplearningdrizzle
- Data science ipython notebooks
- Julia
- Gym
- Regarding satellite images
- Monk Object Detection
- Awesome pytorch list
- Topdeeplearning
- NLPprogress
- Multi task NLP
- Opencv
- Transformers
- Code implementations for research papers
- Tool for visualizing attention in the Transformer model
- Powerful and efficient Computer Vision Annotation Tool (CVAT)
- Powerful and efficient Computer Vision Annotation Tool (CVAT)
- TransCoder
- Super Duper NLP
- Tessellate Imaging
- Machine Learning with Python
- GPT 2
- Data augmentation for NLP
- Mlops
- Reinforcement learning
- keras applications
About CNNs
- LegoNet: Efficient Convolutional Neural Networks with Lego Filters
- MeshCNN, a convolutional neural network designed specifically for triangular meshes
- Octave Convolution
- PyTorch Image Models, ResNet/ResNeXT, DPN, MobileNet-V3/V2/V1, MNASNet, Single-Path NAS, FBNet
- Deep Neural Networks with Box Convolutions
- Invertible Residual Networks
- Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks
- Faster Faster R-CNN Implementation
- Faster R-CNN Another Implementation
- Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
- Wide ResNet model in PyTorch
- DiracNets: Training Very Deep Neural Networks Without Skip-Connections
- An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
- Efficient Densenet
- Video Frame Interpolation via Adaptive Separable Convolution
- Learning local feature descriptors with triplets and shallow convolutional neural networks
- Densely Connected Convolutional Networks
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- Deep Residual Learning for Image Recognition
- Training Wide ResNets for CIFAR-10 and CIFAR-100 in PyTorch
- Deformable Convolutional Network
- Convolutional Neural Fabrics
- Deformable Convolutional Networks in PyTorch
- Dilated ResNet combination with Dilated Convolutions
- Striving for Simplicity: The All Convolutional Net
- Convolutional LSTM Network
- Big collection of pretrained classification models
- PyTorch Image Classification with Kaggle Dogs vs Cats Dataset
- CIFAR-10 on Pytorch with VGG, ResNet and DenseNet
- Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)
- NVIDIA/unsupervised-video-interpolation
About GANs
- Mimicry, PyTorch Library for Reproducibility of GAN Research
- Clean Readable CycleGAN
- StarGAN
- Block Neural Autoregressive Flow
- High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
- A Style-Based Generator Architecture for Generative Adversarial Networks
- GANDissect, PyTorch Tool for Visualizing Neurons in GANs
- Learning deep representations by mutual information estimation and maximization
- Variational Laplace Autoencoders
- VeGANS, library for easily training GANs
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Conditional GAN
- Wasserstein GAN
- Adversarial Generator-Encoder Network
- Image-to-Image Translation with Conditional Adversarial Networks
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- On the Effects of Batch and Weight Normalization in Generative Adversarial Networks
- Improved Training of Wasserstein GANs
- Collection of Generative Models with PyTorch
- Generative Adversarial Nets (GAN)
- Variational Autoencoder (VAE)
- Improved Training of Wasserstein GANs
- CycleGAN and Semi-Supervised GAN
- Improving Variational Auto-Encoders using Householder Flow and using convex combination linear Inverse Autoregressive Flow
- PyTorch GAN Collection
- Generative Adversarial Networks, focusing on anime face drawing
- Simple Generative Adversarial Networks
- Adversarial Auto-encoders
- torchgan: Framework for modelling Generative Adversarial Networks in Pytorch
Thank You for visiting the repo, hope it helped you! I would like to hear suggestions from you!!
Can reach me at
