How can artificial neural networks approximate the brain?

被引：13

作者：

Shao, Feng ^{[1
]}

Shen, Zheng ^{[1
]}

机构：

[1] Peking Univ, Sch Psychol & Cognit Sci, Beijing Key Lab Behav & Mental Hlth, Beijing, Peoples R China

来源：

FRONTIERS IN PSYCHOLOGY | 2023年 / 13卷

关键词：

dual neural node; neuron type; energy source mode; hierarchical architecture; spike-time encoding; emergent computation; executive control to socially cognitive behavior; HUMAN PREFRONTAL CORTEX; PYRAMIDAL NEURONS; DEFAULT MODE; VON ECONOMO; LIFE-SPAN; COMPUTATION; SPIKE; EVOLUTION; DYNAMICS; STORAGE;

D O I：

10.3389/fpsyg.2022.970214

中图分类号：

B84 [心理学];

学科分类号：

04 ; 0402 ;

摘要：

The article reviews the history development of artificial neural networks (ANNs), then compares the differences between ANNs and brain networks in their constituent unit, network architecture, and dynamic principle. The authors offer five points of suggestion for ANNs development and ten questions to be investigated further for the interdisciplinary field of brain simulation. Even though brain is a super-complex system with 10(11) neurons, its intelligence does depend rather on the neuronal type and their energy supply mode than the number of neurons. It might be possible for ANN development to follow a new direction that is a combination of multiple modules with different architecture principle and multiple computation, rather than very large scale of neural networks with much more uniformed units and hidden layers.

引用

页数：14

共 50 条

[1] PRECISION AND APPROXIMATE FLATNESS IN ARTIFICIAL NEURAL NETWORKS
STINCHCOMBE, MB
NEURAL COMPUTATION, 1995, 7 (05) : 1021 - 1039
[2] Design Methodology for Embedded Approximate Artificial Neural Networks
Balaji, Adarsha
Ullah, Salim
Das, Anup
Kumar, Akash
GLSVLSI '19 - PROCEEDINGS OF THE 2019 ON GREAT LAKES SYMPOSIUM ON VLSI, 2019, : 489 - 494
[3] Design of Power-Efficient Approximate Multipliers for Approximate Artificial Neural Networks
Mrazek, Vojtech
Sarwar, Syed Shakib
Sekanina, Lukas
Vasicek, Zdenek
Roy, Kaushik
2016 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER-AIDED DESIGN (ICCAD), 2016,
[4] Neural networks can learn to approximate autonomous flows
Rodriguez, Jose M.
Garzon, Max H.
FLUIDS AND WAVES: RECENT TRENDS IN APPLIED ANALYSIS, 2007, 440 : 197 - 206
[5] Building a Brain: How Convolution Neural Networks Can Predict Sprinkler Activations
de Vries, J.
Kostka, Stanislav
THERMOSENSE: THERMAL INFRARED APPLICATIONS XL, 2018, 10661
[6] How Can Artificial Neural Networks Help Making the Intractable Search Spaces Tractable
Iclanzan, David
Dumitrescu, D.
2008 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1-8, 2008, : 4015 - 4022
[7] ARTIFICIAL METAPLASTICITY CAN IMPROVE ARTIFICIAL NEURAL NETWORKS LEARNING
Andina, Diego
Alvarez-Vellisco, Antonio
Jevtic, Aleksandar
Fombellida, Juan
INTELLIGENT AUTOMATION AND SOFT COMPUTING, 2009, 15 (04): : 683 - 696
[8] Artificial Neural Network Promotion How to introduce Artificial Neural Networks to Students
Dolezel, Petr
Mariska, Martin
Taufer, Ivan
Havlicek, Libor
2013 INTERNATIONAL CONFERENCE ON PROCESS CONTROL (PC), 2013, : 214 - 218
[9] Representations and generalization in artificial and brain neural networks
Li, Qianyi
Sorscher, Ben
Sompolinsky, Haim
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2024, 121 (27)
[10] The Heuristic Work of the Brain and Artificial Neural Networks
Eskov V.M.
Pyatin V.F.
Eskov V.V.
Ilyashenko L.K.
Biophysics, 2019, 64 (2) : 293 - 299

← 1 2 3 4 5 →