释放相似度匹配的潜力：可扩展性、监督与预训练
Unlocking the Potential of Similarity Matching: Scalability, Supervision and Pre-training
AI总结：
针对BP算法的生物合理性与在线学习局限，本文基于相似度匹配框架，提出PyTorch实现的卷积非负SM、局部有监督SM目标，并验证了其在LeNet等架构预训练中的特征评估效果。
摘要：
尽管反向传播（BP）算法有效，但它在生物合理性、计算成本和在线学习适用性方面存在局限。因此，开发依赖局部学习规则的替代性生物合理学习方法日益受到关注。本研究聚焦于主要为无监督的相似度匹配（SM）框架，该框架符合生物系统中的观察机制，并提供在线、局部化和生物合理的算法。i) 为将SM扩展到大型数据集，我们提出了一种使用PyTorch的卷积非负SM实现。ii) 我们引入了一种类似于典型相关分析的局部有监督SM目标，以促进SM层的堆叠。iii) 我们利用PyTorch实现来预训练LeNet等架构，并将特征评估与BP训练的模型进行比较。这项工作将生物合理的算法与计算效率相结合，为进一步探索开辟了多条途径。
英文摘要：
While effective, the backpropagation (BP) algorithm exhibits limitations in terms of biological plausibility, computational cost, and suitability for online learning. As a result, there has been a growing interest in developing alternative biologically plausible learning approaches that rely on local learning rules. This study focuses on the primarily unsupervised similarity matching (SM) framework, which aligns with observed mechanisms in biological systems and offers online, localized, and biologically plausible algorithms. i) To scale SM to large datasets, we propose an implementation of Convolutional Nonnegative SM using PyTorch. ii) We introduce a localized supervised SM objective reminiscent of canonical correlation analysis, facilitating stacking SM layers. iii) We leverage the PyTorch implementation for pre-training architectures such as LeNet and compare the evaluation of features against BP-trained models. This work combines biologically plausible algorithms with computational efficiency opening multiple avenues for further explorations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
