Machine Learning in Science (@mackelab) 's Twitter Profile
Machine Learning in Science

@mackelab

We build probabilistic #MachineLearning and #AI Tools for scientific discovery, especially in Neuroscience. Probably not tweeted by @jakhmack.

ID: 931248410014994432

linkhttp://www.mackelab.org calendar_today16-11-2017 19:51:37

269 Tweet

2,2K Followers

178 Following

Machine Learning in Science (@mackelab) 's Twitter Profile Photo

there is still time for you to make some really good-looking—and state-dependent!—fake LFP or EEG data to up the chances for your Cosyne submission! * * that was (obviously) a joke: Cosyne does not condone the use of LFP or EEG data.

Machine Learning in Science (@mackelab) 's Twitter Profile Photo

Welcome Daniel (Daniel Gedon) to our lab! In his PhD he focussed on time series and low-dimensional representations, and now he will work on model discovery for time series. Outside the lab he's active from biking, to hiking or yoga-ing. Glad to have you join!

Matthijs Pals (@matthijs_pals) 's Twitter Profile Photo

How to find all fixed points in piece-wise linear recurrent neural networks (RNNs)? A short thread 🧵 In RNNs with N units with ReLU(x-b) activations the phase space is partioned in 2^N regions by hyperplanes at x=b 1/7

How to find all fixed points in piece-wise linear recurrent neural networks (RNNs)? 
A short thread 🧵
In RNNs with N units with ReLU(x-b) activations the phase space is partioned in 2^N regions by hyperplanes at x=b 1/7
Auguste Schulz (@schulzauguste) 's Twitter Profile Photo

1) With our NeurIPS Conference poster happening tomorrow, it's about time to introduce our Spotlight paper 🔦, co-lead with Jaivardhan Kapoor : Latent Diffusion for Neural Spiking data (LDNS), a latent variable model (LVM) which addresses 3 goals simultaneously:

1) With our <a href="/NeurIPSConf/">NeurIPS Conference</a> poster happening tomorrow, it's about time to introduce our Spotlight  paper 🔦, co-lead with <a href="/_Jaivardhan_/">Jaivardhan Kapoor</a> :

Latent Diffusion for Neural Spiking data (LDNS), a latent variable model (LVM) which addresses 3 goals simultaneously: