The backpropagation algorithm implemented on spiking neuromorphic hardware
The capabilities of natural neural systems have inspired both new generations of machine
learning algorithms as well as neuromorphic, very large-scale integrated circuits capable of …
learning algorithms as well as neuromorphic, very large-scale integrated circuits capable of …
Spiking lca in a neural circuit with dictionary learning and synaptic normalization
The Locally Competitive Algorithm (LCA)[17, 18] was put forward as a model of primary
visual cortex [14, 17] and has been used extensively as a sparse coding algorithm for …
visual cortex [14, 17] and has been used extensively as a sparse coding algorithm for …
Neko: a library for exploring neuromorphic learning rules
The field of neuromorphic computing is in a period of active exploration. While many tools
have been developed to simulate neuronal dynamics or convert deep networks to spiking …
have been developed to simulate neuronal dynamics or convert deep networks to spiking …
Robust Intrusion Detection for Industrial IoT
Due to the significant role of Industrial Internet of Things (IIoT) in industrial systems, it often
faces numerous network attacks. Therefore, intrusion detection systems are crucial for real …
faces numerous network attacks. Therefore, intrusion detection systems are crucial for real …
Implementing backpropagation for learning on neuromorphic spiking hardware
Many contemporary advances in the theory and practice of neural networks are inspired by
our understanding of how information is processed by natural neural systems. However, the …
our understanding of how information is processed by natural neural systems. However, the …
A Neuromorphic Normalization Algorithm for Stabilizing Synaptic Weights with Application to Dictionary Learning in LCA
Instabilities in neuromorphic machine learning can occur when synaptic updates meant to
encode matrix transforms are not normalized. This phenomenon is encountered in Hebbian …
encode matrix transforms are not normalized. This phenomenon is encountered in Hebbian …
Determining sequences of interactions, process extraction, and robot generation using artificial intelligence/machine learning models
P Singh - US Patent 11,340,917, 2022 - Google Patents
Use of artificial intelligence (AI)/machine learning (ML) models is disclosed to determine
sequences of user interactions with computing systems, extract common processes, and …
sequences of user interactions with computing systems, extract common processes, and …
Determining sequences of interactions, process extraction, and robot generation using artificial intelligence/machine learning models
P Singh - US Patent 11,301,269, 2022 - Google Patents
Use of artificial intelligence (AI)/machine learning (ML) models is disclosed to determine
sequences of user interac tions with computing systems, extract common processes, and …
sequences of user interac tions with computing systems, extract common processes, and …
基于代价敏感学**的恶意 URL 检测研究
蔡勍萌， 王健， **鹏博 - Journal of Cyber Security, 2023 - jcs.iie.ac.cn
随着大数据时代的到来, 恶意URL 作为Web 攻击的媒介渐渐威胁着用户的信息安全.
传统的恶意URL 检测手段如黑名单检测, 签名匹配方法**逐步暴露缺陷, 为此本文提出一种基于 …
传统的恶意URL 检测手段如黑名单检测, 签名匹配方法**逐步暴露缺陷, 为此本文提出一种基于 …
Determining sequences of interactions, process extraction, and robot generation using artificial intelligence/machine learning models
P Singh - US Patent 11,803,397, 2023 - Google Patents
Use of artificial intelligence (AI)/machine learning (ML) models is disclosed to determine
sequences of user interactions with computing systems, extract common processes, and …
sequences of user interactions with computing systems, extract common processes, and …