Dharshan Kumaran - Publications, H-index & Citations

Dharshan Kumaran

google deepmind

48H指数

87论文数

5.4W被引数

收录论文 26

发表时间

Causal evidence that language models use confidence to drive behaviour 因果证据表明语言模型使用置信度来驱动行为

Nature Machine Intelligence

IF23.9

2026-09-07

OAAI

Dharshan Kumaran; Nathaniel Daw; Simon Osindero; Petar Veličković; Viorica Patraucean

Competing Biases underlie Overconfidence and Underconfidence in LLMs 竞争偏见是llm过度自信和不自信的基础

Nature Machine Intelligence

IF23.9

2026-04-22

OAAI

Dharshan Kumaran; Stephen M. Fleming; Larisa Markeeva; Joe Heyward; Andrea Banino; Mrinal Mathur; Razvan Pascanu; Simon Osindero; Benedetto De Martino; Petar Veličković; Viorica Patraucean

Language models, like humans, show content effects on reasoning tasks

PNAS NEXUS

IF3.8

2024-07-16

OAAI

Lampinen, Andrew K.; Dasgupta, Ishita; Chan, Stephanie C. Y.; Sheahan, Hannah R.; Creswell, Antonia; Kumaran, Dharshan; McClelland, James L.; Hill, Felix

Prefrontal Dynamics Associated with Efficient Detours and Shortcuts: A Combined Functional Magnetic Resonance Imaging and Magnetoencenphalography Study

JOURNAL OF COGNITIVE NEUROSCIENCE

IF3

2019-08-01

OAAI

Javadi, Amir-Homayoun; Patai, Eva Zita; Marin-Garcia, Eugenia; Margolis, Aaron; Tan, Heng-Ru M.; Kumaran, Dharshan; Nardini, Marko; Penny, Will; Duzel, Emrah; Dayan, Peter; Spiers, Hugo J.

Backtracking during navigation is correlated with enhanced anterior cingulate activity and suppression of alpha oscillations and the 'default-mode' network

PROCEEDINGS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES

IF3.5

2019-07-31

OAAI

Javadi, Amir-Homayoun; Patai, Eva Zita; Marin-Garcia, Eugenia; Margois, Aaron; Tan, Heng-Ru M.; Kumaran, Dharshan; Nardini, Marko; Penny, Will; Duzel, Emrah; Dayan, Peter; Spiers, Hugo J.

Big-Loop Recurrence within the Hippocampal System Supports Integration of Information across Episodes 海马系统内的大循环复发支持跨发作信息的整合

NEURON

IF15

2018-09-01

OAAI

Koster, Raphael; Chadwick, Martin J.; Chen, Yi; Berron, David; Banino, Andrea; Duezel, Emrah; Hassabis, Demis; Kumaran, Dharshan

NEUROBIOLOGY OF AGING

IF3.5

2018-05-01

107

OAAI

Berron, David; Neumann, Katja; Maass, Anne; Schuetze, Hartmut; Fliessbach, Klaus; Kiven, Verena; Jessen, Frank; Sauvage, Magdalena; Kumaran, Dharshan; Duezel, Emrah

The elastic weight consolidation penalty is empirically valid REPLY

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA

IF9.1

2018-02-20

OAAI

Kirkpatrick, James; Pascanu, Razvan; Rabinowitz, Neil; Veness, Joel; Desjardins, Guillaume; Rusu, Andrei A.; Milan, Kieran; Quan, John; Ramalho, Tiago; Grabska-Barwinska, Agnieszka; Hassabis, Demis; Clopath, Claudia; Kumaran, Dharshan; Hadsell, Raia

Prior preferences beneficially influence social and non-social learning

NATURE COMMUNICATIONS

IF15.7

2017-10-10

OAAI

Tarantola, Tor; Kumaran, Dharshan; Dayan, Peter; De Martino, Benedetto

Neuroscience-Inspired Artificial Intelligence 神经科学启发的人工智能

NEURON

IF15

2017-07-01

890

OAAI

Hassabis, Demis; Kumaran, Dharshan; Summerfield, Christopher; Botvinick, Matthew

Overcoming catastrophic forgetting in neural networks 克服神经网络中的灾难性遗忘

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA

IF9.1

2017-03-14

3.7K

OAAI

Kirkpatricka, James; Pascanu, Razvan; Rabinowitz, Neil; Veness, Joel; Desjardins, Guillaume; Rusu, Andrei A.; Milan, Kieran; Quan, John; Ramalho, Tiago; Grabska-Barwinska, Agnieszka; Hassabis, Demis; Clopath, Claudia; Kumaran, Dharshan; Hadsell, Raia

Computations Underlying Social Hierarchy Learning: Distinct Neural Mechanisms for Updating and Representing Self-Relevant Information

NEURON

IF15

2016-12-01

OAAI

Kumaran, Dharshan; Banino, Andrea; Blundell, Charles; Hassabis, Demis; Dayan, Peter

Semantic representations in the temporal pole predict false memories

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA

IF9.1

2016-08-22

OAAI

Chadwick, Martin J.; Anjum, Raeesa S.; Kumaran, Dharshan; Schacter, Daniel L.; Spiers, Hugo J.; Hassabis, Demis