On-chip unsupervised learning in winner-take-all networks of spiking neurons

2017 ◽  
Author(s):  
Raphaela Kreiser ◽  
Timoleon Moraitis ◽  
Yulia Sandamirskaya ◽  
Giacomo Indiveri
Keyword(s):  
Unsupervised Learning ◽  
Spiking Neurons ◽  
On Chip ◽  
Winner Take All ◽  
Take All

scholarly journals Almost Unsupervised Learning for Dense Crowd Counting

2019 ◽  
Vol 33 ◽  
pp. 8868-8875 ◽  
Author(s):  
Deepak Babu Sam ◽  
Neeraj N Sajjan ◽  
Himanshu Maurya ◽  
R. Venkatesh Babu
Keyword(s):  
Unsupervised Learning ◽  
Large Scale ◽  
Learning Method ◽  
Large Variability ◽  
Proposed Model ◽  
Dense Crowd ◽  
Winner Take All ◽  
Learned Features ◽  
Take All

We present an unsupervised learning method for dense crowd count estimation. Marred by large variability in appearance of people and extreme overlap in crowds, enumerating people proves to be a difficult task even for humans. This implies creating large-scale annotated crowd data is expensive and directly takes a toll on the performance of existing CNN based counting models on account of small datasets. Motivated by these challenges, we develop Grid Winner-Take-All (GWTA) autoencoder to learn several layers of useful filters from unlabeled crowd images. Our GWTA approach divides a convolution layer spatially into a grid of cells. Within each cell, only the maximally activated neuron is allowed to update the filter. Almost 99.9% of the parameters of the proposed model are trained without any labeled data while the rest 0.1% are tuned with supervision. The model achieves superior results compared to other unsupervised methods and stays reasonably close to the accuracy of supervised baseline. Furthermore, we present comparisons and analyses regarding the quality of learned features across various models.

scholarly journals Bio-Inspired Microsystem for Robust Genetic Assay Recognition

2008 ◽  
Vol 2008 ◽  
pp. 1-10 ◽  
Author(s):  
Jaw-Chyng Lue ◽  
Wai-Chi Fang
Keyword(s):  
Single Channel ◽  
Learning Algorithm ◽  
Integrated System ◽  
Sigmoid Function ◽  
Artificial Neural Network Ann ◽  
On Chip ◽  
Winner Take All ◽  
Genetic Assay ◽  
Better Than ◽  
Take All

A compact integrated system-on-chip (SoC) architecture solution for robust, real-time, and on-site genetic analysis has been proposed. This microsystem solution is noise-tolerable and suitable for analyzing the weak fluorescence patterns from a PCR prepared dual-labeled DNA microchip assay. In the architecture, a preceding VLSI differential logarithm microchip is designed for effectively computing the logarithm of the normalized input fluorescence signals. A posterior VLSI artificial neural network (ANN) processor chip is used for analyzing the processed signals from the differential logarithm stage. A single-channel logarithmic circuit was fabricated and characterized. A prototype ANN chip with unsupervised winner-take-all (WTA) function was designed, fabricated, and tested. An ANN learning algorithm using a novel sigmoid-logarithmic transfer function based on the supervised backpropagation (BP) algorithm is proposed for robustly recognizing low-intensity patterns. Our results show that the trained new ANN can recognize low-fluorescence patterns better than an ANN using the conventional sigmoid function.

scholarly journals Efficient k-Winner-Take-All Competitive Learning Hardware Architecture for On-Chip Learning

Sensors ◽  
2012 ◽  
Vol 12 (9) ◽  
pp. 11661-11683
Author(s):  
Chien-Min Ou ◽  
Hui-Ya Li ◽  
Wen-Jyi Hwang
Keyword(s):  
Competitive Learning ◽  
Hardware Architecture ◽  
On Chip ◽  
Winner Take All ◽  
Take All
Sign in / Sign up

Export Citation Format

Share Document