Filters








73 Hits in 7.5 sec

Lossy Compression of Color Images using Lifting Scheme and Prediction Errors

Manoj Kumar, Ankita Vaish
2016 International Journal of Modern Education and Computer Science  
This paper presents an effective compression technique for lossy compression of color images.  ...  Approximation subband is compressed losslessly using prediction errors and Huffman coding, while each of the detail subbands are compressed independently using an effective quantization and Huffman coding  ...  [9] proposed a single bit map BTC (SBBTC) technique for compression of color images using a single bit map to quantize all the three color planes.  ... 
doi:10.5815/ijmecs.2016.04.01 fatcat:jzt2orqtuzdobfpuxwlkn3u5am

The M2DC Project: Modular Microserver DataCentre

Mariano Cecowski, Giovanni Agosta, Ariel Oleksiak, Michal Kierzynka, Micha vor dem Berge, Wolfgang Christmann, Stefan Krupop, Mario Porrmann, Jens Hagemeyer, Rene Griessl, Meysam Peykanu, Lennart Tigges (+13 others)
2016 2016 Euromicro Conference on Digital System Design (DSD)  
This paper provides an overview of the different topics FPGAs have been used for in the last 15 years of research and why they have been chosen over other processing units like e.g. CPUs.  ...  Nevertheless, every application field introduces special requirements to the used computational architecture.  ...  Non-linear auto-regressive (AR) filter structures for a chaos-based frequency hopping sequence generator 2001 [90] Neuro-computing Hopfield neural network mapped into a 2-D systolic array 2001  ... 
doi:10.1109/dsd.2016.76 dblp:conf/dsd/CecowskiAOKBCKP16 fatcat:bu4nbkqaejebjafrotibui6mkq

Meta-Learning Deep Energy-Based Memory Models [article]

Sergey Bartunov, Jack W Rae, Simon Osindero, Timothy P Lillicrap
2021 arXiv   pre-print
Attractor networks provide a sound model of associative memory: patterns are stored as attractors of the network dynamics and associative retrieval is performed by running the dynamics starting from a  ...  We present a novel meta-learning approach to energy-based memory models (EBMM) that allows one to use an arbitrary neural architecture as an energy model and quickly store patterns in its weights.  ...  Yan Wu also helped us with setting up Dynamic Kanerva Machine and reviewing the manuscript.  ... 
arXiv:1910.02720v2 fatcat:cff4puf7gjfi3dws74ttw5hg5y

Morphological Transform for Image Compression

Enrique Guzmán, Oleksiy Pogrebnyak, Cornelio Yañez, Luis Pastor Sanchez Fernandez
2008 EURASIP Journal on Advances in Signal Processing  
Autoassociative and heteroassociative MAMs can be considered as a subclass of morphological neural networks.  ...  The MT is applied to individual blocks of the image using some transformation matrix as an input pattern.  ...  ACKNOWLEDGMENT This work was partially supported by Instituto Politecnico Nacional as a part of the research project SIP no. 20080903.  ... 
doi:10.1155/2008/426580 fatcat:wehtygzhurhsrkuvofbi72ojq4

Searching for Memories, Sudoku, Implicit Check Bits, and the Iterative Use of Not-Always-Correct Rapid Neural Computation

J. J. Hopfield
2008 Neural Computation  
The memory model and a related computational network for solving Sudoku puzzles produce answers that contain implicit check bits in the representation of information across neurons, allowing a rapid evaluation  ...  This information allows more difficult computations or memory retrievals to be done in a serial fashion by using the fast but limited capabilities of a computational module multiple times.  ...  Acknowledgments I thank Kevin and Linda Mottram for introducing me to Sudoku puzzles on a windless day while sailing in the Dodecanese, David Eppstein for providing examples of difficult puzzles, and David  ... 
doi:10.1162/neco.2008.09-06-345 fatcat:5akp4iqezjhmtmxcdxrzdrhmkm

Searching for Memories, Sudoku, Implicit Check Bits, and the Iterative Use of Not-Always-Correct Rapid Neural Computation

J. J. Hopfield
2008 Neural Computation  
The memory model and a related computational network for solving Sudoku puzzles produce answers that contain implicit check bits in the representation of information across neurons, allowing a rapid evaluation  ...  This information allows more difficult computations or memory retrievals to be done in a serial fashion by using the fast but limited capabilities of a computational module multiple times.  ...  Acknowledgments I thank Kevin and Linda Mottram for introducing me to Sudoku puzzles on a windless day while sailing in the Dodecanese, David Eppstein for providing examples of difficult puzzles, and David  ... 
doi:10.1162/neco.2007.09-06-345 pmid:18199026 fatcat:hdkpsymjnrak7dhi3uzpp2txyu

Quantum Optimization and Quantum Learning: A Survey

Yangyang Li, Mengzhuo Tian, Guangyuan Liu, Cheng Peng, Licheng Jiao
2020 IEEE Access  
It is a frontier interdisciplinary subject with a perfect integration of biology, mathematics and other disciplines.  ...  INDEX TERMS Quantum optimization, quantum learning, quantum evolutionary algorithm (QEA), quantum particle swarm algorithm (QPSO), quantum immune clonal algorithm (QICA), quantum neural network (QNN),  ...  Reference [139] proposes a quantum parallel bi-directional self-organizing neural network to realize a real-time pure color image denoising.  ... 
doi:10.1109/access.2020.2970105 fatcat:y765erlnyzakvdj3nv273ccgei

A Review of Deep Learning Algorithms and Their Applications in Healthcare

Hussein Abdel-Jaber, Disha Devassy, Azhar Al Salam, Lamya Hidaytallah, Malak EL-Amir
2022 Algorithms  
Deep learning is a type of machine learning that uses artificial neural networks to mimic the human brain.  ...  Deep learning uses artificial neural networks to recognize patterns and learn from them to make decisions.  ...  Conflicts of Interest: The authors declare no conflict of interest. eferences  ... 
doi:10.3390/a15020071 fatcat:ku5mfuijdjfxxdv7hlkexad7dy

A New Chaotic-Based RGB Image Encryption Technique Using a Nonlinear Rotational 16 × 16 DNA Playfair Matrix

Dina Ibrahim, Kareem Ahmed, Mohamed Abdallah, AbdElmgeid A. Ali
2022 Cryptography  
RGB image encryption ensures the confidentiality of color images during storage and transmission.  ...  In this paper, a novel RGB image encryption technique is proposed for encrypting individual pixels of RGB images using chaotic systems and 16 rounds of DNA encoding, transpositions and substitutions.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/cryptography6020028 fatcat:qveeqdnh6fb4rpb6yc46pownzq

Algorithm and Architecture for a Low-Power Content-Addressable Memory Based on Sparse Clustered Networks

Hooman Jarollahi, Vincent Gripon, Naoya Onizawa, Warren J. Gross
2015 IEEE Transactions on Very Large Scale Integration (vlsi) Systems  
The proposed architecture is based on a recently developed sparse clustered network using binary connections that on-average eliminates most of the parallel comparisons performed during a search.  ...  Index Terms-Associative memory, content-addressable memory (CAM), low-power computing, recurrent neural networks, sparse clustered networks (SCNs). 1063-8210 He was a Visiting Scholar with the Research  ...  [9] , and image coding [10] .  ... 
doi:10.1109/tvlsi.2014.2316733 fatcat:i3zdsmqedranlg4yaaoixq3gsq

Searching for memories, Sudoku, implicit check-bits, and the iterative use of not-always-correct rapid neural computation [article]

J. J. Hopfield
2006 arXiv   pre-print
The memory model and a related computational network for solving Sudoku puzzles produce answers that contain implicit check-bits in the representation of information across neurons, allowing a rapid evaluation  ...  This information allows more difficult computations or memory retrievals to be done in a serial fashion by using the fast but limited capabilities of a computational module multiple times.  ...  Acknowledgments The author thanks Kevin and Linda Mottram for introducing him to Sudoku puzzles on a windless day while sailing in the Dodecanese, David Eppstein for providing examples of difficult puzzles  ... 
arXiv:q-bio/0609006v2 fatcat:drfglpn2ibamjejfoj6cd26tuu

Deep Learning Methods for Human Behavior Recognition

Jia Lu, Minh Nguyen, Wei Qi Yan
2020 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ)  
Since deep learning methods have been well investigated in the past decades, as an end-to-end computational method, it simplifies feature extraction as the operations in a black box.  ...  We proposed Selective Kernel Network (SKNet) and ResNeXt with attention mechanism, which generate positive results to recognize human behaviours.  ...  Hopfield network is a neural network with a single layer fully connected to each other. Each neuron is an input as well as an output.  ... 
doi:10.1109/ivcnz51579.2020.9290640 fatcat:sq4fni6z2nfz5okecnsbmzum6e

Fundamental problems in statistical physics XIV: Lecture on Machine Learning [article]

Aurélien Decelle
2022 arXiv   pre-print
In this short lecture, I will try to present first a brief introduction to Machine Learning from the angle of neural networks.  ...  The case that interests us is the interface with physics, and more specifically statistical physics.  ...  This concludes this introduction to supervised learning, using simple block of neural network.  ... 
arXiv:2202.05670v2 fatcat:s2qh3ypgjbbfbhcd6tqkapdihm

A Critical Review of Recurrent Neural Networks for Sequence Learning [article]

Zachary C. Lipton, John Berkowitz, Charles Elkan
2015 arXiv   pre-print
Recurrent neural networks (RNNs) are connectionist models that capture the dynamics of sequences via cycles in the network of nodes.  ...  Unlike standard feedforward neural networks, recurrent networks retain a state that can represent information from an arbitrarily long context window.  ...  Acknowledgements The first author's research is funded by generous support from the Division of Biomedical Informatics at UCSD, via a training grant from the National Library of Medicine.  ... 
arXiv:1506.00019v4 fatcat:ze5xftnh2zd75fbatpm3iyqmvu

Toward an interpretation of dynamic neural activity in terms of chaotic dynamical systems

Ichiro Tsuda
2001 Behavioral and Brain Sciences  
Block I consists of a recurrent network of a pyramidal-type neuron and a network providing global feedback, whose strength is randomly fixed.  ...  Block II consists of the same network as in block I with the addition of specific negative feedback connections.  ...  We also thank Michael Breakspear and Karl Friston for kindly answering a basic question we asked them on the symmetry they used in their commentary, and Jaroslav Stark, for informing us of many related  ... 
doi:10.1017/s0140525x01000097 fatcat:d2mpwqliqjdetnzhwbktezj4ka
« Previous Showing results 1 — 15 out of 73 results