The Intuition Machine Letter — 1st Edition

Welcome to the bi-weekly letter covering Deep Learning Patterns, Methodology and Strategy. We’ve come up away to organize the topics to appeal to the broadest of audiences. The more general topics always are at the top, while more specialized ones are towards the bottom. We hope that this newsletter we appeal to all those interested in Deep Learning developments.

For this issue, we revisit the Metalearning symposium, introduce courses and tools for AI, look at various ethical viewpoints with regards to the development of AI, see how advances in AI parallel advances in Neurosciences, and explore recent researches and developments on AI.


Metalearning Symposium

Several approaches to metalearning have emerged, including those based on Bayesian optimization, gradient descent, reinforcement learning, and evolutionary computation. The symposium presents an overview of these approaches, given by the researchers who developed them.

Tools and Courses


The new open ecosystem for interchangeable AI models

Machine Learning Crash Course | Google Developers

Educational resources for machine learning

Pandas on Ray — RISE Lab

Pandas on Ray accelerates Pandas queries by 4x on an 8-core machine, only requiring users to change a single line of code in their notebooks.

GitHub — onnx/onnxmltools: ONNXMLTools enables conversion of models to ONNX. Currently supports CoreML and SciKit

GitHub is where people build software. More than 28 million people use GitHub to discover, fork, and contribute to over 80 million projects.

Notes from Coursera Deep Learning courses by Andrew Ng

My notes from the excellent Coursera specialization by Andrew Ng

Project Alexandria — Allen Institute for Artificial Intelligence

Alexandria integrates machine reading and reasoning, natural language understanding, computer vision, and crowdsourcing techniques to create a new extensive, foundational common sense knowledge source for future AI systems to build upon.

The UX of AI — Library — Google Design

Using Google Clips to understand how a human-centered design process elevates artificial intelligence

Queryparser, an Open Source Tool for Parsing and Analyzing SQL

Written in Haskell, Queryparser is Uber Engineering’s open source tool for parsing and analyzing SQL queries that makes it easy to identify foreign-key relationships in large data warehouses.


The Great AI Paradox — MIT Technology Review

Don’t worry about supersmart AI eliminating all the jobs. That’s just a distraction from the problems even relatively dumb computers are causing.

Center for Humane Technology

The Center for Humane Technology is a world-class team of former tech
insiders and CEOs who are advancing thoughtful solutions to change the
culture, business incentives, design techniques, and organizational
structures driving how technology hijacks our brains.

The Real Reason to be Afraid of Artificial Intelligence | Peter Haas

A robotics researcher afraid of robots, Peter Haas, invites us into his world of understand where the threats of robots and artificial intelligence lie. Befo…

How Fast Is AI Progressing? Stanford’s New Report Card for Artificial Intelligence

When? This is probably the question futurists, AI experts, and even people with a keen interest in technology dread most. It’s been famously difficult to predict when developments…

AI in our Daily Life

AI Just Learned How to Boost the Brain’s Memory | WIRED

If we can’t understand our own brains, maybe the machines can do it for us.

Ubisoft’s AI in Far Cry 5 and Watch Dogs could change gaming | WIRED UK

The gaming company’s Commit Assistant AI tool has been trained to spot when programmers are about to make a mistake

Low-cost EEG can now be used to reconstruct images of what you see | KurzweilAI

(left:) Test image displayed on computer monitor. (right:) Image captured by EEG and decoded. (credit: Dan Nemrodov et al./eNeuro) A new technique developed

A Less-Artificial Intelligence — MIT Technology Review

Studying 70,000 mouse neurons could help Andreas Tolias build smarter AI.

How Deep Learning AI Will Help Hologram Technology Find Practical Applications

Not only is the technique an advancement of holographic technology, but also, the holograms could have fascinating (and practical) medical applications.


Counterintuitive Properties of High Dimensional Space — Lost in Spacetime

Visualizing Outliers | FlowingData


HALP: High-Accuracy Low-Precision Training · Stanford DAWN

Low-precision computation has been gaining a lot of traction in machine learning.

Can Neuroevolution Change Machine Learning? | News | Communications of the ACM

Neuroevolution is a form of artificial intelligence that uses evolutionary algorithms to generate artificial neural networks, parameters, topology and rules.

Can increasing depth serve to accelerate optimization? — Off the convex path

Algorithms off the convex path.


Artificial Intuition : The Improbable Deep Learning Revolution

I challenge you to find a field as interesting and exciting as Deep Learning.

The Deep Learning AI Playbook

“Whatever you are studying right now if you are not getting up to speed on deep learning, neural networks, etc., you lose,” says Mark Cuban.
“We are going through the process where software will automate software, automation will automate automation.”

Journal Articles

[1803.00657] Evolutionary Generative Adversarial Networks

[1803.02839v1] The emergent algebraic structure of RNNs and embeddings in NLP

[1802.09419] Stochastic Hyperparameter Optimization through Hypernetworks

[1802.08773] GraphRNN: A Deep Generative Model for Graphs

The Intuition Machine Letter — 1st Edition was originally published in Intuition Machine on Medium, where people are continuing the conversation by highlighting and responding to this story.

Source: Deep Learning on Medium