30+ Machine Learning Resources

30+ Machine Learning Resources

  • May 25, 2018
Table of Contents

30+ Machine Learning Resources

For almost all machine learning projects, the main steps of the ideal solution remain same. Briefly, we all go over the steps below each and every time: Understand the dataClean up, fix the missing values, extract new features, select the best onesBuild the model, compare it with the other ones, tune hyper parameters, find out what is the right metric to evaluate your modelIterate this process over and over again until you believe you have the best solution:) Iterate this process over and over again until you believe you have the best solution:)

During each step, I had to do some research on the web depending on my business object and jotted down the best resources I ran across. The resources include Online Courses, Kernels from Kaggle, Cheat Sheets and Blog Posts. Below I’ve listed them and categorised by each step (all of the resources are free except the ones that have ‘paid’ in the end):

Source: medium.com

Tags :
Share :
comments powered by Disqus

Related Posts

What the History of Math Can Teach Us About the Future of AI

What the History of Math Can Teach Us About the Future of AI

Read More
Tensor Compilers: Comparing PlaidML, Tensor Comprehensions, and TVM

Tensor Compilers: Comparing PlaidML, Tensor Comprehensions, and TVM

One of the most complex and performance critical parts of any machine learning framework is its support for device specific acceleration. Indeed, without efficient GPU acceleration, much of modern ML research and deployment would not be possible. This acceleration support is also a critical bottleneck, both in terms of adding support for a wider range of hardware targets (including mobile) as well as for writing new research kernels.

Read More
A Deep Dive into Monte Carlo Tree Search

A Deep Dive into Monte Carlo Tree Search

The very first Go AIs used multiple modules to handle each aspect of playing Go – life and death, capturing races, opening theory, endgame theory, and so on. The idea was that by having experts program each module using heuristics, the AI would become an expert in all areas of the game. All that came to a grinding halt with the introduction of Monte Carlo Tree Search (MCTS) around 2008.

Read More