Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Martinelli, Flavio"'
Can we identify the weights of a neural network by probing its input-output mapping? At first glance, this problem seems to have many solutions because of permutation, overparameterisation and activation function symmetries. Yet, we show that the inc
Externí odkaz:
http://arxiv.org/abs/2304.12794
MLPGradientFlow is a software package to solve numerically the gradient flow differential equation $\dot \theta = -\nabla \mathcal L(\theta; \mathcal D)$, where $\theta$ are the parameters of a multi-layer perceptron, $\mathcal D$ is some data set, a
Externí odkaz:
http://arxiv.org/abs/2301.10638
Publikováno v:
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Advances of deep learning for Artificial Neural Networks(ANNs) have led to significant improvements in the performance of digital signal processing systems implemented on digital chips. Although recent progress in low-power chips is remarkable, neuro
Externí odkaz:
http://arxiv.org/abs/1910.12459
Publikováno v:
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020, pp. 8544-8548
Recent advances in Voice Activity Detection (VAD) are driven by artificial and Recurrent Neural Networks (RNNs), however, using a VAD system in battery-operated devices requires further power efficiency. This can be achieved by neuromorphic hardware,
Externí odkaz:
http://arxiv.org/abs/1910.09993
Can we recover the hidden parameters of an Artificial Neural Network (ANN) by probing its input-output mapping? We propose a systematic method, called `Expand-and-Cluster' that needs only the number of hidden layers and the activation function of the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::68f93141f87750fbf66b6515815fe300
Bernstein Conference 2022 abstract. http://bernstein-conference.de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bf0595370439aa03a9cb37e2bb4d484b