Neuroscience-Inspired Artificial Intelligence

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

doi:10.1016/j.neuron.2017.06.011

Cited by 1,132 publications

(841 citation statements)

References 130 publications

Supporting

Mentioning

825

Contrasting

Unclassified

Order By: Relevance

“…However, recent evidence suggests that architectures with emergent properties (e.g. in a neural network) can generatively model the world and plan and make decisions based on that model (Hassabis et al, 2017). While an elaboration of these ideas is beyond the scope of this Perspective, our view does not exclude model-based decision-making.…”

Section: Resultsmentioning

confidence: 99%

Economic Choice as an Untangling of Options into Actions

Yoo

Hayden

2018

Neuron

113

123

View full text Add to dashboard Cite

SUMMARY We propose that economic choice can be understood as a gradual transformation from domain of options to one of the actions. We draw an analogy with the idea of untangling information in the form vision system and propose that form vision and economic choice may be two aspects of a larger process that sculpts actions based on sensory inputs. From this viewpoint, choice results from the accumulated effect of repetitions of simple computations. These may consist primarily of relative valuations (evaluations relative to the value of rejection, perhaps in a manner akin to divisive normalization) applied to individual offers. With regard to economic choice, cortical brain regions differ primarily in their position and in what information they prioritize, and do not—with a few exceptions—have categorically distinct roles. Each region’s specific contribution is determined largely by its inputs; thus, understanding connectivity is crucial for understanding choice. This view suggests that there is no single site of choice, that there is no meaningful distinction between pre- and post-decisionality, and that there is no explicit representation of value in the brain.

show abstract

Section: Resultsmentioning

confidence: 99%

Economic Choice as an Untangling of Options into Actions

Yoo

Hayden

2018

Neuron

113

123

View full text Add to dashboard Cite

show abstract

“…[253][254][255] In a well-studied example, memories from the hippocampal region, where memories are first encoded, can be moved to the neocortex in a more permanent form of storage.…”

Section: System Consolidation Of Memorymentioning

confidence: 99%

Bridging Biological and Artificial Neural Networks with Emerging Neuromorphic Devices: Fundamentals, Progress, and Challenges

et al. 2019

View full text Add to dashboard Cite

As the research on artificial intelligence booms, there is broad interest in brain‐inspired computing using novel neuromorphic devices. The potential of various emerging materials and devices for neuromorphic computing has attracted extensive research efforts, leading to a large number of publications. Going forward, in order to better emulate the brain's functions, its relevant fundamentals, working mechanisms, and resultant behaviors need to be re‐visited, better understood, and connected to electronics. A systematic overview of biological and artificial neural systems is given, along with their related critical mechanisms. Recent progress in neuromorphic devices is reviewed and, more importantly, the existing challenges are highlighted to hopefully shed light on future research directions.

show abstract

“…While modern neural networks share these similarities to the brain, whether more fidelity to known brain structures would improve performance is an actively debated question. 4 For example, in computer vision applications, many of the features to which hidden layers are sensitive (such as edges in different orientations) have correlates in the mammalian visual cortex. 5 For neuroimaging, a simple deep learning model may accept image data as a vector composed of voxel intensities, with each voxel serving as an input "neuron."…”

Section: What Is Deep Learning?mentioning

confidence: 99%

Deep Learning in Neuroradiology

Zaharchuk

Gong

Wintermark

et al. 2018

AJNR Am J Neuroradiol

248

169

View full text Add to dashboard Cite

SUMMARY:Deep learning is a form of machine learning using a convolutional neural network architecture that shows tremendous promise for imaging applications. It is increasingly being adapted from its original demonstration in computer vision applications to medical imaging. Because of the high volume and wealth of multimodal imaging information acquired in typical studies, neuroradiology is poised to be an early adopter of deep learning. Compelling deep learning research applications have been demonstrated, and their use is likely to grow rapidly. This review article describes the reasons, outlines the basic methods used to train and test deep learning models, and presents a brief overview of current and potential clinical applications with an emphasis on how they are likely to change future neuroradiology practice. Facility with these methods among neuroimaging researchers and clinicians will be important to channel and harness the vast potential of this new method.ABBREVIATIONS: AD ϭ Alzheimer disease; ADNI ϭ Alzheimer's Disease Neuroimaging Initiative; ASL ϭ arterial spin-labeling; CNN ϭ convolutional neural network;

show abstract

Neuroscience-Inspired Artificial Intelligence

Cited by 1,132 publications

References 130 publications

Economic Choice as an Untangling of Options into Actions

Economic Choice as an Untangling of Options into Actions

Bridging Biological and Artificial Neural Networks with Emerging Neuromorphic Devices: Fundamentals, Progress, and Challenges

Deep Learning in Neuroradiology

Contact Info

Product

Resources

About