Efficient learning of discrete graphical models
Sign Up to like & getrecommendations! Published in 2020 at "Journal of Statistical Mechanics: Theory and Experiment"
DOI: 10.1088/1742-5468/ac3aea
Abstract: Graphical models are useful tools for describing structured high-dimensional probability distributions. Development of efficient algorithms for learning graphical models with least amount of data remains an active research topic. Reconstruction of graphical models that describe… read more here.
Keywords: discrete graphical; graphical models; efficient learning; learning discrete ... See more keywords
An Efficient Learning Algorithm for Direct Training Deep Spiking Neural Networks
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Cognitive and Developmental Systems"
DOI: 10.1109/tcds.2021.3073846
Abstract: It is challenging to train deep spiking neural networks (SNNs) directly due to the difficulties associated with the nondifferentiable neuron model. In this work, an end-to-end learning algorithm based on discrete current-based leaky integrate-and-fire (C-LIF)… read more here.
Keywords: neural networks; deep spiking; training; spiking neural ... See more keywords
Efficient Learning Strategies for Machine Learning-Based Characterization of Aging-Aware Cell Libraries
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Circuits and Systems I: Regular Papers"
DOI: 10.1109/tcsi.2022.3201431
Abstract: Machine learning (ML)-driven standard cell library characterization enables rapid, on-the-fly generation of cell libraries, opening the door for extensive design-space exploration and other, previously infeasible approaches. However, the benefits of ML-based cell library characterization are… read more here.
Keywords: cell; learning strategies; machine learning; cell libraries ... See more keywords
Efficient Learning-Free Keyword Spotting
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"
DOI: 10.1109/tpami.2018.2845880
Abstract: In this article, a method for segmentation-based learning-free Query by Example (QbE) keyword spotting on handwritten documents is proposed. The method consists of three steps, namely preprocessing, feature extraction and matching, which address critical variations… read more here.
Keywords: learning free; query; proposed method; keyword spotting ... See more keywords