Jan Bauer (@japhba) 's Twitter Profile
Jan Bauer

@japhba

PhD student at @GatsbyUCL and @ELSCbrain. Studying the mechanisms behind of intelligence 🧠🤖

ID: 722135133646688256

linkhttp://japhba.github.io calendar_today18-04-2016 18:50:07

15 Tweet

67 Followers

167 Following

Jan Bauer (@japhba) 's Twitter Profile Photo

Which systems come to mind when reading this? A lot seems to be vaguely familiar in terms of building complex software and testing…

Andrej Karpathy (@karpathy) 's Twitter Profile Photo

Greg Brockman 💯 reminds me of MAML meta-learning (arxiv.org/abs/1703.03400) where the objective is to find weights of a network such that any new task finetunes fast. In Software 1.0 land, equivalent is writing code such that any new desired functionality is simple and doesn't need a refactor.

Kording Lab 🦖 (@kordinglab) 's Twitter Profile Photo

We often discuss if the brain does something like gradient descent. Here is me discussing the issue for Open Neuromorphic. I focus on exposing the weaknesses of the hypothesis as well. Should be particularly useful for newly interested people. youtube.com/watch?v=E5hATe…

Science of Science (@mishateplitskiy) 's Twitter Profile Photo

The longer people are in academia, the more they realize that when reading papers it's best to ignore Intro, Discussion etc. and just look at Methods and Results journals.plos.org/plosone/articl…

The longer people are in academia, the more they realize that when reading papers it's best to ignore Intro, Discussion etc. and just look at Methods and Results
journals.plos.org/plosone/articl…
Thomas Kipf (@tkipf) 's Twitter Profile Photo

Couldn't agree more: we still don't have good solutions for scalable abstraction/concept learning from "raw" data (be it language, vision, or other sensory data). Solving this would likely unlock important new capabilities.

Jan Bauer (@japhba) 's Twitter Profile Photo

pip ⊂ conda ⊂ docker Choose the minimum feasible isolation, but no less (Lightweight but Brittle vs Involved but Stable).

Bruno Gavranović (@bgavran3) 's Twitter Profile Photo

"Even rocks, while not agents per se, track the state of their environment: the interior of a rock “knows” that the environment must be well below the melting point of rock. As systems become more elaborate, they can represent more about the things to which they couple."

Jan Bauer (@japhba) 's Twitter Profile Photo

Had a lot of fun thinking about the neural basis of cognitive flexibility with Alex, Kai, and Ali! Excited to see what other work bridging ML and Cognition will come out of the Analytical Connections summer school 🤖🧠