Nature Search

Demonstration of transformer-based ALBERT model on a 14nm analog AI inference chip

The authors report the implementation of a Transformer-based model on the same architecture used in Large Language Models in a 14nm analog AI accelerator with 35 million Phase Change Memory devices, which achieves near iso-accuracy despite hardware imperfections and noise.

An Chen
Stefano Ambrogio
Geoffrey W. Burr
ResearchOpen Access30 Sept 2025
Nature Communications

Volume: 16, P: 1-11
The design of analogue in-memory computing tiles

This Perspective examines the design of non-volatile memristive analogue in-memory computing tiles for deep neural network accelerators, considering the challenges and opportunities associated with designing the different components and providing projections for how technology scaling may impact key design elements.

Abhairaj Singh
Manuel Le Gallo
Abu Sebastian
Reviews19 Dec 2025
Nature Electronics

Volume: 8, P: 1156-1169
Some Immunologic Considerations in Focal Scleroderma and Progressive Systemic Sclerosis in Children

Virgil Hanson
Helen K Kornreich
Geoffrey A Macpherson
Research01 Sept 1974
Pediatric Research

Volume: 8, P: 806-809
Efficient scaling of large language models with mixture of experts and 3D analog in-memory computing

This study shows a viable pathway to the efficient deployment of state-of-the-art large language models using mixture of experts on 3D analog in-memory computing hardware.

Julian Büchel
Athanasios Vasilopoulos
Abu Sebastian
Research08 Jan 2025
Nature Computational Science

Volume: 5, P: 13-26
Expectancy-related changes in firing of dopamine neurons depend on orbitofrontal cortex

The orbitofrontal cortex (OFC) has been hypothesized to carry information regarding the value of expected rewards. Such information could be used for generating instructive error signals conveyed by dopamine neurons. Here the authors report that this is indeed the case. However, contrary to the simplest hypothesis, OFC lesions did not result in the loss of all value information. Instead, lesions caused the loss of value information derived from model-based representations.

Yuji K Takahashi
Matthew R Roesch
Geoffrey Schoenbaum
Research30 Oct 2011
Nature Neuroscience

Volume: 14, P: 1590-1597
Optimised weight programming for analogue memory-based deep neural networks

Device-level complexity represents a big shortcoming for the hardware realization of analogue memory-based deep neural networks. Mackin et al. report a generalized computational framework, translating software-trained weights into analogue hardware weights, to minimise inference accuracy degradation.

Charles Mackin
Malte J. Rasch
Geoffrey W. Burr
ResearchOpen Access30 Jun 2022
Nature Communications

Volume: 13, P: 1-12
Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators

Analog in-memory computing promises efficient DNN inference acceleration but suffers from nonidealities. Here, hardware-aware training methods are improved so that various larger DNNs of diverse topologies nevertheless achieve iso-accuracy.

Malte J. Rasch
Charles Mackin
Vijay Narayanan
ResearchOpen Access30 Aug 2023
Nature Communications

Volume: 14, P: 1-18
Equivalent-accuracy accelerated neural-network training using analogue memory

Analogue-memory-based neural-network training using non-volatile-memory hardware augmented by circuit simulations achieves the same accuracy as software-based training but with much improved energy efficiency and speed.

Stefano Ambrogio
Pritish Narayanan
Geoffrey W. Burr
Research06 Jun 2018
Nature

Volume: 558, P: 60-67
Clinical trial links oncolytic immunoactivation to survival in glioblastoma

Treatment with the oncolytic herpes virus CAN-3110 is associated with improved survival responses in patients with recurrent glioblastoma, particularly in individuals who are seropositive for HSV1.

Alexander L. Ling
Isaac H. Solomon
E. Antonio Chiocca
ResearchOpen Access18 Oct 2023
Nature

Volume: 623, P: 157-166
A role for optics in AI hardware

Experiments show how an all-optical version of an artificial neural network — a type of artificial-intelligence system — could potentially deliver better energy efficiency can conventional computing approaches.

Geoffrey W. Burr
News & Views08 May 2019
Nature

Volume: 569, P: 199-200
Protecting maize from rootworm damage with the combined application of arbuscular mycorrhizal fungi, Pseudomonas bacteria and entomopathogenic nematodes

Geoffrey Jaffuel
Nicola Imperiali
Bruce E. Hibbard
ResearchOpen Access28 Feb 2019
Scientific Reports

Volume: 9, P: 1-12
A role for analogue memory in AI hardware

Memristor-based chips could lead the way to fast, energy-efficient AI hardware accelerators.

Geoffrey W. Burr
News & Views07 Jan 2019
Nature Machine Intelligence

Volume: 1, P: 10-11
Insights into social insects from the genome of the honeybee Apis mellifera

George M. Weinstock
Gene E. Robinson
Rita Wright
Research26 Oct 2006
Nature

Volume: 443, P: 931-949
Resistive switching materials for information processing

Resistive switching materials enable novel, in-memory information processing, which may resolve the von Neumann bottleneck. This Review focuses on how the switching mechanisms and the resultant electrical properties lead to various computing applications.

Zhongrui Wang
Huaqiang Wu
J. Joshua Yang
Reviews13 Jan 2020
Nature Reviews Materials

Volume: 5, P: 173-195

Search

Demonstration of transformer-based ALBERT model on a 14nm analog AI inference chip

The design of analogue in-memory computing tiles

Some Immunologic Considerations in Focal Scleroderma and Progressive Systemic Sclerosis in Children

Efficient scaling of large language models with mixture of experts and 3D analog in-memory computing

Expectancy-related changes in firing of dopamine neurons depend on orbitofrontal cortex

Optimised weight programming for analogue memory-based deep neural networks

Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators

Equivalent-accuracy accelerated neural-network training using analogue memory

Clinical trial links oncolytic immunoactivation to survival in glioblastoma

A role for optics in AI hardware

Protecting maize from rootworm damage with the combined application of arbuscular mycorrhizal fungi, Pseudomonas bacteria and entomopathogenic nematodes

A role for analogue memory in AI hardware

Insights into social insects from the genome of the honeybee Apis mellifera

Resistive switching materials for information processing

Search

Quick links

Search

Filter By:

Search

Quick links