Machine Learning

Reproducibility

• Why Git and Git-LFS is not enough to solve the Machine Learning Reproducibility crisis

Awesome Machine Learning

A collection of awesome machine learning goodies

• What can TensorFlow really do?
• The First World Class Overview of AI for the General Public
• Fast.ai
• Deep Learning From Scratch: Theory and Implementation
• Cheat sheets for AI, neural networks, machine learning, deep learning and big data
• Resources for learning statistics and machine learning
• Machine Learning Mind Map
• Deep Learning Drizzle
• Rethinking generalization requires revisiting old ideas: statistical mechanics approaches and complex learning behavior
• Explosion on GitHub
  • Thinc
  • Prodigy
  • SpaCy

Podcast

• Andrew Ng: Influential leader in artificial intelligence
• Integrate.ai

Platforms

• Deep Learning Studio
• Google Cloud AI Hub
• PrimeHub

eLearning

• Introduction to Machine Learning
• Coursera: Machine Learning by Andrew Ng
• Stanford CS229: Machine Learning by Andrew Ng
• CS231n: Convolutional Neural Networks for Visual Recognition
• Python Implementation of Andrew Ng’s Machine Learning Course
• Colah’s Blog: Christopher Olah writes about machine learning
• Introduction to Deep Learning - Deep Learning basics with Python, TensorFlow and Keras
• Machine Learning Tutorials
• Artificial Intelligence - All in One
• Google AI Education
• Dive into Deep Learning

Books

• Hands-On Machine Learning with Scikit-Learn and TensorFlow
  • A series of Jupyter notebooks
• Deep Learning
• Data Science 100 UBC

Applications

• Project ideas

Autonomous driving

• Semantic segmentation

Natural Language Processing

Tools

• OpenDeep
• Small survey on ML tools

PyTorch

• PyTorch Lightning by Grid.ai

TensorFlow

• TensorFlow Tutorials
• Awesome TensorFlow
• TensorFlow Hub
• TFX
• TensorFlow User Contributions
• TensorFlow Playground: Tinker With a Neural Network Right Here in Your Browser. Don’t Worry, You Can’t Break It. We Promise.
• Deep Learning Development with Google Colab, TensorFlow, Keras & PyTorch
• Image Classification using Flowers dataset
• Troubleshooting a TensorFlow Predictive Model Microservice with Weave Cloud

Keras

• Awesome Keras
• Keras Resources

Google Colab

• How to run object detection and segmentation on video fast for free
• Quick guide to run TensorBoard in Google Colab

Jupyter

• JupyterHub in Classrooms
• Dockerized Jupyterhub Deep Learning Notebooks with GPU Access
• Jupyter ServerExtension to sync a git repository one-way to a local path
• JupyterHub Ecosystem

XGBoost

• An End-to-End Guide to Understand the Math behind XGBoost

Scala

• Top 15 Scala Libraries for Data Science in 2018
• Keynote: The Last Hope for Scala’s Infinity War - John A. De Goes
• Sean Glover

Apache Spark MLlib

• Databricks courses
• PySpark Uploader
• Analytics for Apache Spark
• Real time sentiment analysis of twitter hashtags with Spark
• Productionizing Spark ML pipelines with the portable format for analytics
• Spark Bench
• Sentiment Analysis of Twitter Hashtags With Spark
• Building A Linear Regression with PySpark and MLlib
• Spark TensorFlow Example
• spark-tensorflow-connector
• Pandas vs Spark
• Get Started with PySpark and Jupyter Notebook in 3 Minutes
• Dataproc cluster with Datalab and the Google Python Client API
• Spark Cheat Sheet

Databricks

• Introduction to Databricks
• Databricks Delta: A Unified Management System for Real-time Big Data
• Real-Time Data Pipelines Made Easy with Structured Streaming in Apache Spark
• Databricks Community

Java

• Search Maven packages
• Jupyter Spark 117 - jar files

MLeap

• MLeap documentation
• MLeap Benchmark
• MLeap demo
• MLeap deploy Spark ML pipelines to production API servers

Courses

• Advanced Spark streaming with MLeap

Kubernetes

• Start from here!
• Kubeflow
• Introduction to Kubeflow on Google Kubernetes Engine
• Deploying a containerized web application
• Polyaxon, Argo and Seldon for model training, package and deployment in Kubernetes
• Cloud Native Computing Foundation
• Juju k8s-tf-demo
• ksonnet
• Continuously Train & Deploy Spark ML and Tensorflow AI Models from Jupyter Notebook to Production
• Kubeflow on EKS
• Kubeflow labs on Azure
• Deploy Kubeflow on GCP
• Feast

FfDL

• Deploy and use a multi-framework deep learning platform on Kubernetes
• Serve it hot! Deploy your FfDL trained models using Seldon
• IBM CODAIT - Center for Open-source Data & AI Technologies

Jupyter

• Zero to JupyterHub with Kubernetes

Cloud Foundry

• Data Science on Cloud Foundry
• Data Science How-To: Text Analytics-as-a-Service
• Car diagnostic API
• Portfolio Optimization
• Operationalizing PySpark Data Science Models on Pivotal Cloud Foundry
• Linear Regression
• PySpark App CF
• PySpark buildpack
• Python buildpack

Dask

Graphistry

Machine Learning Algorithms

Recursive Neural Networks

• Time Series Prediction with LSTM Recurrent Neural Networks in Python with Keras
• How to do time series prediction using RNNs, TensorFlow and Cloud ML Engine

Reinforcement Learning

• Dopamine: a research framework for fast prototyping of reinforcement learning algorithms
• RL Lab
• Reinforcement Learning and Optimal Control

AutoML

• Awesome AutoML
• Auto-sklearn

Machine Learning in Production

• Databricks Delta: A Unified Management System for Real-time Big Data
• Databricks runtime
• Azure Databricks
• MLeap: Productionize Data Science Workflows Using Spark
• Combust
• Rapids.ai
• H2O
• Algorithmia
• Seldon
• Anaconda Enterprise
• Amazon SageMaker
• Azure Machine Learning
• IBM Watson Machine Learning
• The road to 1.0: production ready PyTorch
• Chainer
• MapR Analytics and ML
• Omniscience
• URSA LABS
• Comparing Machine Learning as a Service: Amazon, Microsoft Azure, Google Cloud AI, IBM Watson

Edge Computing

• Sylabs (Singularity)

TensorFlow

• TFX: A TensorFlow-Based Production-Scale Machine Learning Platform

Benchmarks

• Simple/limited/incomplete benchmark for scalability, speed and accuracy of machine learning libraries for classification

Model exchange

• PMML
• PFA
  • Portable Format for Analytics: moving models to production
  • Aardpfark
• ONNX
• CoreML

Platforms

• FloydHub

Datasets

• Google BigQuery Public Datasets
• Datasets publicly available on Google BigQuery
• Awesome Public Datasets
• Fleet maintenance
• Google Genomics Public Dataset
• Google Sample Datasets
• UC Irvine Machine Learning Repository

Research

• BAIR

Companies

• AI in UK Report 2018

Feedback

Was this page helpful?

Yes No

Glad to hear it! Please tell us how we can improve.

Sorry to hear that. Please tell us how we can improve.