Machine Learning Up to Date #7

OmegaNeo’s RL and Representation Learning Architecture [Source]

Here's ML UTD #7 from the LifeWithData blog! We help you separate the signal from the noise in today's hectic front lines of software engineering and machine learning.

LifeWithData strives to deliver curated machine learning & software engineering updates that point the reader to key developments without superfluous details. This enables frequent, concise updates across the industry without information overload.



Beating Atari Pong Without Backpropagation

OmegaNeo’s RL and Representation Learning Architecture [Source]
Ogma AI, which uses a multidisciplinary approach to AI technology development, released a neat demo recently. Building off their “OgmaNeo 2” model, they augmented it to train an RL agent without backpropagation. By releasing the backpropagation constraint, they were able to train an agent on a Raspberry Pi to perform quite well at Atari Pong (also on the Pi).
... keep reading
The Rundown

The Disappearing People Project

Snippet from the demo video [Source]
You’ll either love this one or start running for the hills in a tin foil hat. Codepen user @jasonmayes has a demo of real-time removal of video foreground in javascript. Translation: making Harry Potter’s invisibility cloak a reality.
... keep reading
The Rundown

Make a Renaissance Photo of Yourself

Make your own photo [Source]
AI artist “Al Gahaku” has a nice web page where you can use his AI-powered Renaissance-style photo generator. Upload a photo that has a good line-of-sight on your face, and a few clicks later you’ll have something to gawk or laugh about. I tried it out for myself. Not too shabby!
... keep reading
The Rundown

Overview of TinyML

[Source]
Pete Warden gave a nice talk on “tiny ML”, the focus on marrying machine learning with low-power hardware for IoT applications. Pete is the technical lead of the Tensorflow mobile and embedded team at Google, and was previously CTO of Jetpac, which was acquired in 2014.
... keep reading

Generating Music in the Waveform Domain

A block diagram of a time domain generative music model [Source]
Generative machine learning models have become extremely popular in the image and text domains. GPT-3, anyone? However, the same level of success has not been achieved yet in audio. To date, most techniques to achieve audio generation occur in the frequency domain, due to lower dimensionality. This comes at a cost, as re-synthesizing the generated frequency samples is non-trivial. If you’ve ever wanted to delve more into the audio machine learning space, then Sander Dieleman’s article is for you. Grab a cup of your favorite beverage, soak in some sunlight, and let him take you on a tour of generative audio modeling in the time domain.
... keep reading
The Rundown

A Visual Guide to Evolutionary Strategies

A visual progression of OpenAI’s adaptation of REINFORCE-ES [Source]
David Ha (@hardmaru) put together a friendly yet informative explanation of evolutionary strategies as applied in various RL environments. What started with this article ended with me looking through several pages of his fantastic blog (linked below). I highly recommend it.
... keep reading

Connected Papers

[Source]
Self-attention papers, visualized. A few years back, I had a great idea. I figured it would be fun to use the [arXiv](https://arxiv.org/) API to traverse paper citations, eventually creating a nice graph visualization of it all. Well, It’s been done several times. The most recent one I’ve found, Connected Papers, is quite good.
... keep reading