- Google Agrees to Pay Out $118 Million To Former Employees In Gender Discrimination And Pay Equity Suit
Google agrees to pay $118M to 15,000 female employees who were paid $17,000 less than men with the same job titles. Notably this case was filed in California state court, for violating CA’s Equal Pay Act, and the court allowed the women to file as a class.
https://deadline.com/2022/06/google-agrees-to-pay-out-118-million-to-former-1235043474/ - Becoming a magician
- google/evojax
We just released EvoJAX, a hardware-accelerated neuroevolution toolkit built on top of JAX!
EvoJAX can run a wide range of evolution experiments within minutes on a TPU/GPU, compared to hours or days on CPU clusters.
Check it out:
https://github.com/google/evojax
https://arxiv.org/abs/2202.05008 https://twitter.com/hardmaru/status/1492014816403148803/photo/1 - EvoJAX: Hardware-Accelerated Neuroevolution
Evolutionary computation has been shown to be a highly effective method for
training neural networks, particularly when employed at scale on CPU clusters.
Recent work have also showcased their effectiveness on hardware accelerators,
such as GPUs, but so far such demonstrations are tailored for very specific
tasks, limiting applicability to other domains. We present EvoJAX, a scalable,
general purpose, hardware-accelerated neuroevolution toolkit. Building on top
of the JAX library, our toolkit enables neuroevolution algorithms to work with
neural networks running in parallel across multiple TPU/GPUs. EvoJAX achieves
very high performance by implementing the evolution algorithm, neural network
and task all in NumPy, which is compiled just-in-time to run on accelerators.
We provide extensible examples of EvoJAX for a wide range of tasks, including
supervised learning, reinforcement learning and generative art. Since EvoJAX
can find solutions to most of these tasks within minutes on a single
accelerator, compared to hours or days when using CPUs, our toolkit can
significantly shorten the iteration cycle of evolutionary computation
experiments. EvoJAX is available at https://github.com/google/evojax - Conformal Prediction Intervals for Markov Decision Process Trajectories
Before delegating a task to an autonomous system, a human operator may want a
guarantee about the behavior of the system. This paper extends previous work on
conformal prediction for functional data and conformalized quantile regression
to provide conformal prediction intervals over the future behavior of an
autonomous system executing a fixed control policy on a Markov Decision Process
(MDP). The prediction intervals are constructed by applying conformal
corrections to prediction intervals computed by quantile regression. The
resulting intervals guarantee that with probability $1-?$ the observed
trajectory will lie inside the prediction interval, where the probability is
computed with respect to the starting state distribution and the stochasticity
of the MDP. The method is illustrated on MDPs for invasive species management
and StarCraft2 battles. - AlphaFold2.ipynb – Colaboratory
ColabFold: AlphaFold2 using MMseqs2
Easy to use protein structure and complex prediction using AlphaFold2 and Alphafold2-multimer. Sequence alignments/templates are generated through MMseqs2 and HHsearch. For more details, see bottom of the notebook, checkout the ColabFold GitHub and read our manuscript. Old versions: v1.0, v1.1, v1.2, v1.3
Mirdita M, Schütze K, Moriwaki Y, Heo L, Ovchinnikov S, Steinegger M. ColabFold: Making protein folding accessible to all. Nature Methods, 2022 - Zylberschtein Bagels – Delicatessen & Bakery
- Towards designing a generic and comprehensive deep reinforcement learning framework – Applied Intelligence
????This reinforcement learning paper from Nguyen et al is both delightfully illustrated, and a solid overview of key RL terms / methods / frameworks.
"We design a deep RL-based framework that strictly ensures flexibility, robustness, and scalability." https://link.springer.com/article/10.1007/s10489-022-03550-z https://twitter.com/DynamicWebPaige/status/1528930114758537216/photo/1
- Taking Datasets, DataLoaders, and PyTorch’s New DataPipes for a Spin
The PyTorch team recently announced TorchData, a prototype library focused on implementing composable and reusable data loading utilities for PyTorch. I hone…
Digest powered by RSS Digest