4.8 Article

Catalyzing next-generation Artificial Intelligence through NeuroAI

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Editorial Material Biology

Neuroscience needs evolution

Paul Cisek et al.

Summary: The nervous system is shaped by its evolutionary history, offering valuable insights into understanding the brain. This article highlights the importance of evolution in neuroscience and provides specific examples of how evolutionary theory enhances our understanding of neural mechanisms and brain organization.

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES (2022)

Correction Biochemical Research Methods

SLEAP: A deep learning system for multi-animal pose tracking (vol 19, pg 486, 2022)

Talmo D. Pereira et al.

NATURE METHODS (2022)

Article Computer Science, Artificial Intelligence

Social impact and governance of AI and neurotechnologies

Kenji Doya et al.

Summary: Advances in artificial intelligence and brain science will have a significant impact on society, providing immense benefits but also posing risks such as abuse and inequity. It is important to incorporate ethical principles in practical ways and learn from democratic mechanisms and open discussions.

NEURAL NETWORKS (2022)

Article Multidisciplinary Sciences

Dendrocentric learning for synthetic intelligence

Kwabena Boahen

Summary: The study proposes a new learning method for artificial intelligence called dendrocentric learning, which arranges the input signals along dendrites to overcome the thermal constraints of three-dimensional chips. This approach allows for efficient AI computation with low power consumption.

NATURE (2022)

Article Neurosciences

Continuous Whole-Body 3D Kinematic Recordings across the Rodent Behavioral Repertoire

Jesse D. Marshall et al.

Summary: CAPTURE is a new behavioral monitoring system that combines motion capture and deep learning techniques to continuously track the movements of a rat's head, trunk, and limbs in freely behaving animals for up to a week. This system shows significant improvement in precision and robustness compared to existing convolutional network approaches, allowing researchers to comprehensively profile natural rodent behavior and investigate its variations across individuals. By using CAPTURE, researchers can explore a wider range of behaviors and contexts and gain new insights into natural behavior and its neural basis.

NEURON (2021)

Article Computer Science, Artificial Intelligence

Natural and Artificial Intelligence: A brief introduction to the interplay between AI and neuroscience research

Tom Macpherson et al.

Summary: Neuroscience and artificial intelligence have a long history of collaboration, with advances in computer processing power leading to the development of in silico neural networks that mimic biological systems. AI is now capable of advanced perceptual and cognitive abilities, and is increasingly being used as a tool for neuroscience research, transforming our understanding of brain functions. Excitingly, neuroscience-inspired AI also holds promise for understanding changes in brain networks that result in psychopathologies, and could even be utilized in treatment regimes.

NEURAL NETWORKS (2021)

Article Multidisciplinary Sciences

Embodied intelligence via learning and evolution

Agrim Gupta et al.

Summary: The new framework of deep evolutionary reinforcement learning evolves agents with diverse morphologies to learn difficult tasks in complex environments, revealing insights into the relationships between environmental physics, embodied intelligence, and rapid learning evolution. Research indicates that environmental complexity fosters the evolution of morphological intelligence, and that more physically stable and energy efficient morphologies facilitate learning and control. Additionally, a morphological Baldwin effect is demonstrated, where evolution rapidly selects morphologies that learn faster, impacting the behaviors learned and expressed throughout generations.

NATURE COMMUNICATIONS (2021)

Article Engineering, Electrical & Electronic

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

Mike Davies et al.

Summary: Neuromorphic computing aims to develop chips inspired by biological neural circuits to process new knowledge, adapt, behave, and learn in real time at low power levels, with recent advancements showing promising results with Intel's Loihi processor. Compelling neuromorphic networks using spike-based hardware demonstrate significantly lower latency and energy consumption compared to state-of-the-art conventional approaches, solving diverse problems representative of brain-like computation.

PROCEEDINGS OF THE IEEE (2021)

Review Neurosciences

Engineering a Less Artificial Intelligence

Fabian H. Sinz et al.

NEURON (2019)

Article Engineering, Electrical & Electronic

Neuroscience-Inspired Online Unsupervised Learning Algorithms: Artificial neural networks

Cengiz Pehlevan et al.

IEEE SIGNAL PROCESSING MAGAZINE (2019)

Article Multidisciplinary Sciences

A critique of pure learning and what artificial neural networks can learn from animal brains

Anthony M. Zador

NATURE COMMUNICATIONS (2019)

Review Behavioral Sciences

Toward evolutionary and developmental intelligence

Kenji Doya et al.

CURRENT OPINION IN BEHAVIORAL SCIENCES (2019)

Article Multidisciplinary Sciences

Hierarchical motor control in mammals and machines

Josh Merel et al.

NATURE COMMUNICATIONS (2019)

Review Computer Science, Artificial Intelligence

Designing neural networks through neuroevolution

Kenneth O. Stanley et al.

NATURE MACHINE INTELLIGENCE (2019)

Article Neurosciences

DeepLabCut: markerless pose estimation of user-defined body parts with deep learning

Alexander Mathis et al.

NATURE NEUROSCIENCE (2018)

Article Computer Science, Artificial Intelligence

Why We Need a Physically Embodied Turing Test and What It Might Look Like

Charles L. Ortiz et al.

AI MAGAZINE (2017)

Article Psychology, Biological

Building machines that learn and think like people

Brenden M. Lake et al.

BEHAVIORAL AND BRAIN SCIENCES (2017)

Review Neurosciences

Neuroscience-Inspired Artificial Intelligence

Demis Hassabis et al.

NEURON (2017)

Article Multidisciplinary Sciences

Mastering the game of Go with deep neural networks and tree search

David Silver et al.

NATURE (2016)

Article Multidisciplinary Sciences

Human-level control through deep reinforcement learning

Volodymyr Mnih et al.

NATURE (2015)

Article Engineering, Multidisciplinary

Thermal soaring flight of birds and unmanned aerial vehicles

Zsuzsa Akos et al.

BIOINSPIRATION & BIOMIMETICS (2010)

Article Biochemistry & Molecular Biology

The cost of cortical computation

P Lennie

CURRENT BIOLOGY (2003)

Article Computer Science, Artificial Intelligence

Deep blue

M Campbell et al.

ARTIFICIAL INTELLIGENCE (2002)

Review Endocrinology & Metabolism

An energy budget for signaling in the grey matter of the brain

D Attwell et al.

JOURNAL OF CEREBRAL BLOOD FLOW AND METABOLISM (2001)