Back to first-pass browser

First-pass extracted concept

deep neural networks

Candidate: concept label1 source documents4 linked claims
Jump to explainersJump to evidenceJump to sourcesJump to claims
Live refresh every 5sNext refresh in 5s

Aliases

artificial neural networks

Extracted Explainers

What the tool is doing

Deep neural networks are presented as a framework for modeling biological vision and brain information processing while also driving advances in computer vision. The abstract frames them as artificial systems inspired by the brain.

Source 1DOIPubMed

What problem it solves

They help perform high-level visual recognition and provide computational models for studying vision-related information processing.

Source 1DOIPubMed

What it does not solve

The abstract states that current models are designed for engineering goals rather than explicitly to model brain computations.

Source 1DOIPubMed

Alternatives

The abstract contrasts convolutional feedforward networks with future biologically faithful feedforward and recurrent computational models.

Source 1DOIPubMed

Evidence Snippets

Recent advances in neural network modeling have enabled major strides in computer vision and other artificial intelligence applications.
Evidence 1Source 1DOIPubMedprovenance

Supporting Sources

Linked Claims

Claim 1capabilitysupports2015Source 1DOIPubMed

Recent advances in neural network modeling have enabled major strides in computer vision and other artificial intelligence applications.

Claim 2limitationsupports2015Source 1DOIPubMed

Current models are designed with engineering goals rather than to model brain computations.

Claim 3performance trendsupports2015Source 1DOIPubMed

Human-level visual recognition abilities are coming within reach of artificial systems.

Claim 4representational alignmentsupports2015Source 1DOIPubMed

Initial studies comparing internal representations between current neural network models and primate brains find surprisingly similar representational spaces.