Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Computing, Performance and Communication Systems
  4. Vol 10, Issue 1, 2026

A Review of the Evolution of Core Neural Network Models in Deep Learning

Download as PDF

DOI: 10.23977/cpcs.2026.100102 | Downloads: 0 | Views: 36

Author(s)

Suyang Wu 1

Affiliation(s)

1 School of Electronic and Information Engineering, University of Science and Technology Liaoning, Anshan, China

Corresponding Author

Suyang Wu

ABSTRACT

As a core technical branch in the field of artificial intelligence, the development of deep learning is inseparable from the continuous iteration of neural network models. Starting from early neural network models, this paper systematically sorts out the birth background and key technical breakthroughs of core models such as Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), and Transformers. It deeply analyzes the structural characteristics, application scenarios, and inherent limitations of each model. On this basis, it summarizes the core logic of the evolution of deep learning models, such as the transformation from local dependency to global dependency, and from sequential processing to parallel computing. Combined with the current technological development trend, it looks forward to the future development directions of neural network models, such as lightweight and modularization, providing a reference for research and application in related fields.

KEYWORDS

Deep Learning; Neural Networks; Model Evolution; Core Logic; Development Prospect

CITE THIS PAPER

Suyang Wu. A Review of the Evolution of Core Neural Network Models in Deep Learning. Computing, Performance and Communication Systems (2026) Vol. 10: 9-16. DOI: http://dx.doi.org/10.23977/cpcs.2026.100102.

REFERENCES

[1] McCulloch, Warren S., and Walter Pitts. "A logical calculus of the ideas immanent in nervous activity." The bulletin of mathematical biophysics 5.4 (1943): 115-133.
[2] Rosenblatt, Frank. "The perceptron: a probabilistic model for information storage and organization in the brain." Psychological review 65.6 (1958): 386.
[3] Minsky, Marvin, and Seymour Papert. "An introduction to computational geometry." Cambridge tiass., HIT 479.480 (1969): 104.
[4] Rumelhart, David E., Geoffrey E. Hinton, and Ronald J. Williams. "Learning representations by back-propagating errors." nature 323.6088 (1986): 533-536.
[5] Fukushima, Kunihiko. "Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position." Biological cybernetics 36.4 (1980): 193-202.
[6] LeCun, Yann, et al. "Gradient-based learning applied to document recognition." Proceedings of the IEEE 86.11 (2002): 2278-2324.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 3476
Visits: 232401

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.