Self-Growing Binary Activation Network: A Novel Deep Learning Model With Dynamic Architecture

MNIST数据库 计算机科学 建筑 人工智能 天基建筑 冗余(工程) 网络体系结构 深度学习 人工神经网络 二进制数 过程(计算) 任务(项目管理) 功能(生物学) 机器学习 参考体系结构 软件体系结构 软件 工程类 数学 艺术 计算机安全 算术 系统工程 进化生物学 视觉艺术 生物 程序设计语言 操作系统
作者
Ze-Yang Zhang,Yidong Chen,Changle Zhou
出处
期刊:IEEE transactions on neural networks and learning systems [Institute of Electrical and Electronics Engineers]
卷期号:35 (1): 624-633 被引量:4
标识
DOI:10.1109/tnnls.2022.3176027
摘要

For a deep learning model, the network architecture is crucial as a model with inappropriate architecture often suffers from performance degradation or parameter redundancy. However, it is experiential and difficult to find the appropriate architecture for a certain application. To tackle this problem, we propose a novel deep learning model with dynamic architecture, named self-growing binary activation network (SGBAN), which can extend the design of a fully connected network (FCN) progressively, resulting in a more compact architecture with higher performance on a certain task. This constructing process is more efficient than neural architecture search methods that train mass of networks to search for the optimal one. Concretely, the training technique of SGBAN is based on the function-preserving transformations that can expand the architecture and combine the information in the new data without neglecting the knowledge learned in the previous steps. The experimental results on four different classification tasks, i.e., Iris, MNIST, CIFAR-10, and CIFAR-100, demonstrate the effectiveness of SGBAN. On the one hand, SGBAN achieves competitive accuracy when compared with the FCN composed of the same architecture, which indicates that the new training technique has the equivalent optimization ability as the traditional optimization methods. On the other hand, the architecture generated by SGBAN achieves 0.59% improvements of accuracy, with only 33.44% parameters when compared with the FCNs composed of manual design architectures, i.e., 500+150 hidden units, on MNIST. Furthermore, we demonstrate that replacing the fully connected layers of the well-trained VGG-19 with SGBAN can gain a slightly improved performance with less than 1% parameters on all these tasks. Finally, we show that the proposed method can conduct the incremental learning tasks and outperform the three outstanding incremental learning methods, i.e., learning without forgetting, elastic weight consolidation, and gradient episodic memory, on both the incremental learning tasks on Disjoint MNIST and Disjoint CIFAR-10.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
加菲猫发布了新的文献求助10
刚刚
jamin911关注了科研通微信公众号
1秒前
2秒前
like1994发布了新的文献求助10
3秒前
4秒前
shilong.yang发布了新的文献求助20
6秒前
sunny关注了科研通微信公众号
6秒前
包子完成签到,获得积分10
7秒前
7秒前
豆dou发布了新的文献求助10
8秒前
9秒前
请叫我风吹麦浪应助科研采纳,获得10
10秒前
seannnnnnn完成签到 ,获得积分10
11秒前
机灵安白发布了新的文献求助10
11秒前
卡列宁的微笑完成签到,获得积分10
11秒前
李爱国应助Saluzi采纳,获得10
12秒前
14秒前
量子星尘发布了新的文献求助10
14秒前
在水一方应助like1994采纳,获得150
14秒前
14秒前
俏皮蜜蜂发布了新的文献求助10
14秒前
16秒前
半城微凉应助Ethan采纳,获得10
16秒前
nanlinhua完成签到,获得积分10
17秒前
清脆的雁丝完成签到,获得积分10
18秒前
善良的人发布了新的文献求助10
19秒前
周周发布了新的文献求助10
19秒前
科研通AI5应助彼岸花开采纳,获得10
20秒前
沐青应助科研通管家采纳,获得50
21秒前
Jasper应助科研通管家采纳,获得10
21秒前
22秒前
22秒前
hi应助科研通管家采纳,获得10
22秒前
hi应助科研通管家采纳,获得10
22秒前
22秒前
桐桐应助科研通管家采纳,获得10
22秒前
JamesPei应助科研通管家采纳,获得10
22秒前
小马甲应助科研通管家采纳,获得10
22秒前
米尔的猫应助科研通管家采纳,获得20
22秒前
bkagyin应助科研通管家采纳,获得10
22秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Toward a Combinatorial Approach for the Prediction of IgG Half-Life and Clearance 500
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3970004
求助须知:如何正确求助?哪些是违规求助? 3514701
关于积分的说明 11175468
捐赠科研通 3250051
什么是DOI,文献DOI怎么找? 1795187
邀请新用户注册赠送积分活动 875630
科研通“疑难数据库(出版商)”最低求助积分说明 804925