Search Results for author:
Found 9 papers, 3 papers with code
Lyfe Agents: Generative agents for low-cost real-time social interactions
Meanwhile, our techniques enabled Lyfe Agents to operate at a computational cost 10-100 times lower than existing alternatives.
To reverse engineer an entire nervous system
More fundamentally, reconstructing or modeling a system is an important milestone in understanding it, and so, simulating an entire nervous system is in itself one of the goals, indeed dreams, of systems neuroscience.
Dual policy as self-model for planning
In such dual-policy agents, a model-free policy and a distilled policy are used for model-free actions and planned actions, respectively.
Neural Foundations of Mental Simulation: Future Prediction of Latent Representations on Dynamic Scenes
In particular, we find that neural responses are currently best predicted by models trained to predict the future state of their environment in the latent space of pretrained foundation models optimized for dynamic scenes in a self-supervised manner.
Biological key-value memory networks
In neuroscience, classical Hopfield networks are the standard biologically plausible model of long-term memory, relying on Hebbian plasticity for storage and attractor dynamics for recall.
Biological learning in key-value memory networks
In neuroscience, classical Hopfield networks are the standard biologically plausible model of long-term memory, relying on Hebbian plasticity for storage and attractor dynamics for recall.
Artificial neural networks for neuroscientists: A primer
Artificial neural networks (ANNs) are essential tools in machine learning that have drawn increasing attention in neuroscience.
Understanding the functional and structural differences across excitatory and inhibitory neurons
We found that neurons that project to higher-order areas will have greater stimulus selectivity, regardless of whether they are excitatory or not.
A Dataset and Architecture for Visual Reasoning with a Working Memory
COG is much simpler than the general problem of video analysis, yet it addresses many of the problems relating to visual and logical reasoning and memory -- problems that remain challenging for modern deep learning architectures.
