Weekly Selection — Nov 24, 2017
Estimating an Optimal Learning Rate For a Deep Neural Network
by Pavel Surmenok — 6 min read
In this post, I’m describing a simple and powerful way to find a reasonable learning rate that I learned from fast.ai Deep Learning course. I’m taking the new version of the course in person at University of San Francisco.
Demystifying “Matrix Capsules with EM Routing.” Part 1: Overview
by Sahaj Garg — 13 min read
Recently, Geoffrey Hinton, one of the fathers of deep learning, made waves in the machine learning community by publishing a revolutionary computer vision architecture: capsule networks. Hinton has been pushing for using capsule networks since 2012, after he first revolutionized the use of Convolutional Neural Networks (CNNs) for image detection, but only now has he made them feasible.
Three Common Mistakes With Company-level Dashboards
by Chris Dowsett — 4 min read
Company-level dashboards are special. They hold the most important Key Performance Indicators (KPIs) across each department and business area.
Thoughts on JAMA’s “Adapting to Artificial Intelligence” by Jha and Topol
by Leonard D'Avolio PhD — 6 min read
When journalists write about the disruptive power of artificial intelligence in healthcare they tend to zero in on radiology and pathology and for good reason. Both trades involve the interpretation of patterns from quantifiable image data — a thing that AI has proven highly capable of in several studies and commercial applications from facial recognition to the classification of hotdogs.
5 Data Storytelling Tips for Creating More Persuasive Charts and Graphs
by Payman Taei — 9 min read
Working with numbers isn’t usually thought of as a sexy job. After all, occupations like accounting and data entry aren’t exactly the most exciting vocations in this digital era.
Reinforcement Learning: The quirks
by Dominic Monn — 3 min read
I have been applying variations of the A3C and the GA3C algorithm on various OpenAI Gym environments as part of my internship. I did not have any extensive Reinforcement Learning experience before that, apart from some introduction courses, so this was very new to me.
Why you should forget ‘for-loop’ for data science code and embrace vectorization
by Tirthajyoti Sarkar — 4 min read
We all have used for-loops for majority of the tasks which needs an iteration over a long list of elements. I am sure almost everybody, who is reading this article, wrote their first code for matrix or vector multiplication using a for-loop back in high-school or college.
Computer Vision by Andrew Ng — 11 Lessons Learned
by Ryan Shrott — 6 min read
I recently completed Andrew Ng’s computer vision course on Coursera. Ng does an excellent job at explaining many of the complex ideas required to optimize any computer vision task.
Can We Please Stop Using Word Clouds
by Claire Lesage — 5 min read
There are a lot of interesting and more scientific problems in Natural Language Processing, but I’m here today to share just an opinion with you. Word clouds are big-time ugly.
