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

AI and Compute

AI and Compute

We’re releasing an analysis showing that since 2012, the amount of compute used in the largest AI training runs has been increasing exponentially with a 3.5 month-doubling time (by comparison, Moore’s Law had an 18-month doubling period). Since 2012, this metric has grown by more than 300,000x (an 18-month doubling period would yield only a 12x increase). Improvements in compute have been a key component of AI progress, so as long as this trend continues, it’s worth preparing for the implications of systems far outside today’s capabilities.

Read More
Intel AI Lab open-sources library for deep learning-driven NLP

Intel AI Lab open-sources library for deep learning-driven NLP

The Intel AI Lab has open-sourced a library for natural language processing to help researchers and developers give conversational agents like chatbots and virtual assistants the smarts necessary to function, such as name entity recognition, intent extraction, and semantic parsing to identify the action a person wants to take from their words. The first-ever conference by Intel for AI developers is being held Wednesday and Thursday, May 23 and 24, at the Palace of Fine Arts in San Francisco. The Intel AI Lab now employs about 40 data scientists and researchers and works with divisions of the company developing products like the nGraph framework and hardware like Nervana Neural Network chips, Liu said.

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