Encoding of speech in convolutional layers and the brain stem based on language experience
Sign Up to like & getrecommendations! Published in 2022 at "Scientific Reports"
DOI: 10.1101/2022.01.03.474864
Abstract: Comparing artificial neural networks with outputs of neuroimaging techniques has recently seen substantial advances in (computer) vision and text-based language models. Here, we propose a framework to compare biological and artificial neural computations of spoken… read more here.
Keywords: intermediate convolutional; language; brain; brain stem ... See more keywords
Domain Wall Memory-Based Design of Deep Neural Network Convolutional Layers
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Access"
DOI: 10.1109/access.2020.2968081
Abstract: In the hardware implementation of deep learning algorithms such as, convolutional neural networks (CNNs) and binarized neural networks (BNNs), multiple dot products and memories for storing parameters take a significant portion of area and power… read more here.
Keywords: wall memory; domain wall; based design; convolutional layers ... See more keywords
Asymptotic Spectral Representation of Linear Convolutional Layers
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Signal Processing"
DOI: 10.1109/tsp.2022.3140718
Abstract: By stacking a number of convolutional layers, convolutional neural networks (CNNs) have made remarkable performance boosts in many artificial intelligence applications. While the convolution operation is well-understood, it is still a mystery why repeated convolutions… read more here.
Keywords: upper bounds; spectral representation; representation linear; asymptotic spectral ... See more keywords
Evaluating the Learning Procedure of CNNs through a Sequence of Prognostic Tests Utilising Information Theoretical Measures
Sign Up to like & getrecommendations! Published in 2022 at "Entropy"
DOI: 10.3390/e24010067
Abstract: Deep learning has proven to be an important element of modern data processing technology, which has found its application in many areas such as multimodal sensor data processing and understanding, data generation and anomaly detection.… read more here.
Keywords: theoretical measures; convolutional layers; information; information theoretical ... See more keywords