进化多目标神经架构 通过两阶段优化搜索二元神经网络
IEEE transactions on cybernetics
|January 13, 2026
概括
本研究介绍了对二进制神经网络 (BNN) 的多目标进化神经架构搜索 (NAS). 拟议的MO-TS-BNAS算法有效平衡模型大小和错误,优化资源有限的设备的BNN.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 二元神经网络 (BNNs) 为资源有限的环境提供极端模型压缩.
- 设计高效的BNN架构是具有挑战性的,因为专门的二元化操作.
- 神经架构搜索 (NAS) 为高性能BNN设计提供了一个可行的解决方案.
研究的目的:
- 为BNN提出一个多目标进化NAS算法 (MO-TS-BNAS).
- 为满足具有不同参数大小和性能水平的网络需求.
- 为了优化BNN架构设计,平衡模型大小和错误.
主要方法:
- 在BNN训练中使用ApproxSign函数进行梯度近似.
- 在非主导分类中引入了辅助目标,以减轻小模型陷.
- 实施了两阶段的训练策略,包括路径脱落和改进的迷你批次梯度下降.
- 为进行比较分析,对全精度基线搜索空间进行了二进制化.
主要成果:
- MO-TS-BNAS算法成功地平衡了模型大小和错误目标.
- 在CIFAR10和ImageNet数据集上的实验验证证明了该方法的有效性.
- 拟议的方法优化了BNN架构,以满足各种性能要求.
结论:
- MO-TS-BNAS是设计高性能BNN架构的有效方法.
- 该算法解决了BNN架构搜索中的关键挑战,包括模型大小和准确性权衡.
- 这项工作促进了BNN在移动和资源有限的环境中的应用.
相关概念视频
Multi-input and Multi-variable systems
385
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
In the absence of...
385
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
284
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
284
Neural Circuits
2.6K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
2.6K
Optimization Problems
8
Optimization problems often involve identifying maximum or minimum values under specific constraints. A well-known example is determining the longest horizontal pipe that can be moved around a right-angled corner, where a 3-meter-wide hallway meets a 2-meter-wide hallway. This scenario, common in architectural design and industrial transport, can be understood conceptually through geometric and trigonometric reasoning.To visualize the problem, consider the pipe as a straight line that touches...
8
Neural Regulation
43.1K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
43.1K


