towards_entropy (@Towards_Entropy) header
towards_entropy (@Towards_Entropy) profile picture

Stuck in vector space

Joined July 2018
Photo by towards_entropy (@Towards_Entropy)Photo by towards_entropy (@Towards_Entropy)Photo by towards_entropy (@Towards_Entropy)Photo by towards_entropy (@Towards_Entropy)Photo by towards_entropy (@Towards_Entropy)Photo by towards_entropy (@Towards_Entropy)Photo by towards_entropy (@Towards_Entropy)Photo by towards_entropy (@Towards_Entropy)Photo by towards_entropy (@Towards_Entropy)Photo by towards_entropy (@Towards_Entropy)
#compchem #machinelearning people, what's the current best out-of-the-box GNN prediction library for small molecules? trying to use chemprop but finding it impossible
2
3
3
seriously though making the only entrypoint to your code a 900 line args file has to be one of the worst design decisions I've ever seen
towards_entropy retweeted
New paper: an end-to-end approach for learning to simulate coarse-grained molecular dynamics! - Multi-scale GNN - complex systems: polymers and batteries - very long stable rollouts - orders of magnitude faster than classical force fields! arxiv.org/abs/2204.10348 🧵1/n
5
57
4
286
towards_entropy retweeted
4
26
2
131
towards_entropy retweeted
Today we release MRL, an open source python package for #drugdiscovery built on @RDKit_org, @PyTorch and #nbdev. MRL combines generative models, reinforcement learning and #cheminformatics to accelerate drug design. Stay tuned for more! github.com/DarkMatterAI/mrl
1
2
4
towards_entropy retweeted
2
4
43
What's the current status of the Linearity hypothesis for adversarial examples? Trying to reconcile some contradictory information.
1
1
2
However, there's this from Deepmind which presents contradictory information arxiv.org/pdf/1811.09716.pdf The authors find that robustness via adversarial training is achieved by decreasing the curvature of the loss landscape, effectively making the network more linear
1
2
Has anyone followed up on this? Is linearity at the logit level good or bad? If it's good, what explains the Church window plots from pdfs.semanticscholar.org/b5e…
Mean squared error is derived from maximum likelihood assuming p(y|x) is Gaussian. Are there derivations for loss functions following the same procedure using a different assumed distribution? Specifically something fat tailed, like a Levy distribution
1
5
Are there any publications on neural architecture search for LSTM/GRU cell variants? Or really any recent exploration on recurrent cell design
1
1
1
I'm aware of Greff (arxiv.org/pdf/1503.04069.pdf) and Jozefowicz (proceedings.mlr.press/v37/jo…) on the topic, but both papers are from 2015. It feels like the tools/compute available have evolved enough since then that a more expansive investigation should be possible
1
1
When the paper says "details can be found in the Supplementary Information" but there is no supplementary information
Training a StyleGAN from scratch is not helping to quiet the voice in my head telling me to splurge on a 4 GPU machine