RECORD
SA-CNN: Application to text categorization issues using simulated annealing-based convolutional neural network optimization
Machine Learning · Submitted 13 Mar 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Experiments demonstrate that we can achieve greater classification accuracy than earlier models with manual tuning, and the improvement in time and space for exploration relative to human tuning is substantial.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Convolutional neural networks (CNNs) are a representative class of deep learning algorithms including convolutional computation that perform translation-invariant classification of input data based on their hierarchical architecture. However, classical convolutional neural network learning methods use the steepest descent algorithm for training, and the learning performance is greatly influenced by the initial weight settings of the convolutional and fully connected layers, requiring re-tuning to achieve better performance under different model structures and data. Combining the strengths of the simulated annealing algorithm in global search, we propose applying it to the hyperparameter search process in order to increase the effectiveness of convolutional neural networks (CNNs). In this paper, we introduce SA-CNN neural networks for text classification tasks based on Text-CNN neural networks and implement the simulated annealing algorithm for hyperparameter search. Experiments demonstrate that we can achieve greater classification accuracy than earlier models with manual tuning, and the improvement in time and space for exploration relative to human tuning is substantial.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Convolutional neural networks (CNNs) are a representative class of deep learning algorithms including convolutional computation that perform translation-invariant classification of input data based on their hierarchical architecture. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | However, classical convolutional neural network learning methods use the steepest descent algorithm for training, and the learning performance is greatly influenced by the initial weight settings of the convolutional and fully connected layers, requiring re-tuning to achieve better performance under different model structures and data. | background 0.64 | 0.09 | 0.02 | asserted 1.00 |
| s2 | Combining the strengths of the simulated annealing algorithm in global search, we propose applying it to the hyperparameter search process in order to increase the effectiveness of convolutional neural networks (CNNs). | contribution 0.81 | 0.49 | 0.08 | asserted 0.77 |
| s3 | In this paper, we introduce SA-CNN neural networks for text classification tasks based on Text-CNN neural networks and implement the simulated annealing algorithm for hyperparameter search. | contribution 0.73 | 0.92 | 0.08 | asserted 1.00 |
| s4 | Experiments demonstrate that we can achieve greater classification accuracy than earlier models with manual tuning, and the improvement in time and space for exploration relative to human tuning is substantial. | result 1.00 | 0.95 | 0.85 | asserted 0.96 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Convolutional neural networks (CNNs) are a representative class of deep learning algorithms including convolutional computation that perform translation-invariant classification of input data based on their hierarchical architecture. However, classical convolutional neural network learning methods use the steepest descent algorithm for training, and the learning performance is greatly influenced by the initial weight settings of the convolutional and fully connected layers, requiring re-tuning to achieve better performance under different model structures and data. Combining the strengths of the simulated annealing algorithm in global search, we propose applying it to the hyperparameter search process in order to increase the effectiveness of convolutional neural networks (CNNs). In this paper, we introduce SA-CNN neural networks for text classification tasks based on Text-CNN neural networks and implement the simulated annealing algorithm for hyperparameter search. Experiments demonstrate that we can achieve greater classification accuracy than earlier models with manual tuning, and the improvement in time and space for exploration relative to human tuning is substantial.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 1 sentence without a confident label
Compares with 1 paper
-
* CNN-multichannel: A mix of CNN-static and CNN-non-static, i.e. two types of inputs. * DCNN [ref] : Dynamic Convolutional Neural Network with k-max pooling. * MV-RNN [ref] : Matrix-Vector Recursive Neural Network with parse trees.
A Convolutional Neural Network for Modelling Sentences · Introduction to the comparison model · 0.91
Cites as background 2 papers
-
Rie Johnson and Tong Zhang [ref] applied CNNs to high-dimensional text data and learned with embed small text regions for classification.
Effective Use of Word Order for Text Categorization with Convolutional Neural Networks · Introduction · 0.98
-
Google proposed the BERT model [ref] , which overcomes the problem that static word vectors cannot solve the problem of a word having multiple meanings.
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding · The current utilisation text classification in neural networks · 0.98
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.