Jan 27, 2020Evolving Game of Life: Neural Networks, Chaos, and ComplexityCan a neural network learn the rules to Conway’s Game of Life? Why, and how? It’s pretty clear now that deep learning is not, by itself, the answer to artificial general intelligence (AGI). Neural nets often work well but only in the domain they were trained in, without true understanding…Artificial Intelligence6 min readArtificial Intelligence6 min read
Sep 4, 2019It happened again. I gave control of my Robinhood account to an AI.This time, it gets even more intriguing: using attention to predict stock prices, it worked, and there were some weird discoveries along the way. Back in January, I gave over control of my Robinhood stock trading account to an AI that I’d made. Many people read, and responded to, the…Machine Learning12 min readMachine Learning12 min read
Feb 10, 2019Member-onlyHere’s what happened when I gave control of my Robinhood account to an AI for a week… and how I built the AI. Robinhood, if you don’t know it, is a commission-free stock trading platform that Bay Area techies like me love. I can buy and sell shares very conveniently from my phone. …Finance11 min readFinance11 min read
Published in Towards Data Science·Nov 25, 2018Member-onlyThere are two very different ways to deploy ML models, here’s bothIf an ML model makes a prediction in Jupyter, is anyone around to hear it? Probably not. Deploying models is the key to making them useful. It’s not only if you’re building product, in which case deployment is a necessity — it also applies if you’re generating reports for management…Programming9 min readProgramming9 min read
Published in Towards Data Science·Oct 15, 2018Python has a built-in Logo Turtle, and it’s great for reinforcement learningA little while ago I was teaching a Berkeley class on data analytics, and one of the exercises had students go through the Python stdlib to find interesting modules. I went through the docs too and was delighted to find that Python has a turtle! Do you remember? FORWARD 10 LEFT…Machine Learning7 min readMachine Learning7 min read
Published in Towards Data Science·Sep 2, 2018A blundering guide to making a deep actor-critic bot for stock tradingTechnical analysis lies somewhere on the scale of wishful thinking to crazy complex math. …Machine Learning12 min readMachine Learning12 min read
Jul 10, 2018Hacker’s Guide To The AWS DeepLensIt took me a long time to get started with my DeepLens: it’s a confusing, buggy piece of kit. You’re supposed to use it with various AWS services called things like GreenGrass and SageMaker, but as a hacker I needed to figure it out at a low level by SSHing…Raspberry Pi7 min readRaspberry Pi7 min read
Published in Towards Data Science·May 15, 2018Deep Learning a Monty Hall Strategy (or, a gentle introduction to Deep-Q learning and OpenAI Gym with PyTorch)You never know how a combination of events is going to affect you. For me, bingeing an old episode of Brooklyn-99, combined with Tensorflow’s recent announcement that they’ve officially incorporated the Edward probabalistic programming library, set me to thinking about Bayesian probability for the first time in a while. In…Machine Learning13 min readMachine Learning13 min read
Apr 22, 2018Gliders over the US: Conway’s Game of Life with zip codesIt’d be really interesting to model the success and failure over time of US zip codes. I’ve been thinking about how to use multi-agent simulation to model how population groups evolve over time. This weekend, instead of doing that, I decided to make something pretty instead: if each zip code…Design4 min readDesign4 min read
Apr 17, 2018I modeled my co-workers using our office Slack chats. The results were awesomenian.Generative AI is magical. Faced with a large, personalized text dataset, the average data-inclined engineer has but one choice: train a neural network on it, to predict new text. The idea behind the network is simple: given a character and some historical context, make a prediction about what the next…Machine Learning5 min readMachine Learning5 min read
