Search Results for author:
Found 10 papers, 2 papers with code
Simulating 500 million years of evolution with a language model
Among the generations that we synthesized, we found a bright fluorescent protein at a far distance (58% sequence identity) from known fluorescent proteins, which we estimate is equivalent to simulating five hundred million years of evolution.
Graph Neural Networks Gone Hogwild
Message passing graph neural networks (GNNs) would appear to be powerful tools to learn distributed algorithms via gradient descent, but generate catastrophically incorrect predictions when nodes update asynchronously during inference.
Neuromechanical Autoencoders: Learning to Couple Elastic and Neural Network Nonlinearity
In this work, we seek to develop machine learning analogs of this process, in which we jointly learn the morphology of complex nonlinear elastic solids along with a deep neural network to control it.
Meta-PDE: Learning to Solve PDEs Quickly Without a Mesh
Partial differential equations (PDEs) are often computationally challenging to solve, and in many settings many related PDEs must be be solved either at every timestep or for a variety of candidate boundary conditions, parameters, or geometric domains.
Randomized Automatic Differentiation
The successes of deep learning, variational inference, and many other fields have been aided by specialized implementations of reverse-mode automatic differentiation (AD) to compute gradients of mega-dimensional objectives.
On Predictive Information in RNNs
Certain biological neurons demonstrate a remarkable capability to optimally compress the history of sensory inputs while being maximally informative about the future.
On Predictive Information Sub-optimality of RNNs
Certain biological neurons demonstrate a remarkable capability to optimally compress the history of sensory inputs while being maximally informative about the future.
Scalable Model Compression by Entropy Penalized Reparameterization
We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to a reparameterization.
Counterfactual Image Networks
However, when a layer is removed, the model learns to produce a different image that still looks natural to an adversary, which is possible by removing objects.
Predicting Motivations of Actions by Leveraging Text
In this paper, we introduce the problem of predicting why a person has performed an action in images.
