John Hopfield
PulseAugur coverage of John Hopfield — every cluster mentioning John Hopfield across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New method conditions protein generation using stochastic attention
Researchers have developed a novel method for conditioning protein generation using a training-free stochastic-attention sampler. By incorporating a multiplicity ratio into the sampler's logits, the generation process c…
-
Energy-guided Recursive Model enhances neural network reasoning with Hopfield energies · 2 sources tracked
Researchers have introduced the Energy-guided Recursive Model (ERM), a novel approach to recursive reasoning in neural networks. ERM utilizes explicit Hopfield energies to guide the selection of candidate trajectories, …
-
New Transformer Architecture Integrates Attractor Dynamics for Enhanced Performance
Researchers have introduced the Controlled Dynamics Attractor Transformer (CDAT), a novel architecture that merges transformer self-attention mechanisms with associative memory frameworks. CDAT integrates a mixture von …
-
John Hopfield's 1982 paper reshaped neural network history
A 1982 paper by John Hopfield significantly influenced the field of neural networks, offering a new perspective on their history and development. This foundational work has had a lasting impact on subsequent research an…
-
New model links astrocyte-gated memory dynamics to emergent self-attention
Researchers have developed a new associative memory model that incorporates astrocyte-like gain modulation to achieve emergent self-attention. This model, based on a Hopfield-type network, uses a coupled neuron-astrocyt…
-
New model shows self-attention emerging from astrocyte-gated associative memory
Researchers have developed a novel associative memory model inspired by astrocyte-neuron interactions in the brain. This model utilizes astrocytic gains to dynamically modulate neuron connectivity, leading to a form of …
-
Google DeepMind scientists win Nobel Prize for AI-driven protein discovery
Demis Hassabis and John Jumper of Google DeepMind, along with David Baker from the University of Washington, have been awarded the Nobel Prize in Chemistry for their work on predicting and designing novel proteins. Thei…