Suchergebnisse - computer learning and pattern recognition::(evolutionary OR evolution) computing

Q-learning enhanced differential evolution for feature selection in high-dimensional medical data analysis von Huang, Chenliang, Wang, Mingjing, Asghar, Heidari Ali, Wang, Zhilin, Chen, Huiling

“… In this study, we propose a hybrid optimization algorithm named QDEHHO, where Differential Evolution (DE …”
Volltext

Interpolation consistency training for semi-supervised learning von Verma, Vikas, Kawaguchi, Kenji, Lamb, Alex, Kannala, Juho, Solin, Arno, Bengio, Yoshua, Lopez-Paz, David

“… We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm …”
Volltext

Explainability in deep reinforcement learning von Heuillet, Alexandre, Couthouis, Fabien, Díaz-Rodríguez, Natalia

“… for reinforcement learning (RL), has not been extensively studied. We review recent works in the direction to attain Explainable Reinforcement Learning (XRL …”
Volltext

Deep Learning for Classification of Hyperspectral Data: A Comparative Review von Audebert, Nicolas, Le Saux, Bertrand, Lefevre, Sebastien

“… In recent years, deep-learning techniques revolutionized the way remote sensing data are processed …”
Volltext

Hand-Gesture Recognition Based on EMG and Event-Based Camera Sensor Fusion: A Benchmark in Neuromorphic Computing von Ceolini, Enea, Frenkel, Charlotte, Shrestha, Sumit Bam, Taverni, Gemma, Khacef, Lyes, Payvand, Melika, Donati, Elisa

“… Nowadays, with the increasing use of technology, hand-gesture recognition is considered to be an important aspect of Human-Machine Interaction (HMI …”
Volltext

Learning Accurate Performance Predictors for Ultrafast Automated Model Compression von Wang, Ziwei, Lu, Jiwen, Xiao, Han, Liu, Shengyu, Zhou, Jie

“… In this paper, we propose an ultrafast automated model compression framework called SeerNet for flexible network deployment. Conventional non-differen-tiable …”
Volltext

How evolution learns to generalise: Using the principles of learning theory to understand the evolution of developmental organisation von Kouvaris, Kostas, Clune, Jeff, Kounios, Loizos, Brede, Markus, Watson, Richard A.

“… One of the most intriguing questions in evolution is how organisms exhibit suitable phenotypic variation to rapidly adapt in novel selective environments …”
Volltext

Learning to compare image patches via convolutional neural networks von Zagoruyko, Sergey, Komodakis, Nikos

“… ) a general similarity function for comparing image patches, which is a task of fundamental importance for many computer vision problems …”
Volltext

Fast and Accurate Terrain Image Classification for ASTER Remote Sensing by Data Stream Mining and Evolutionary-EAC Instance-Learning-Based Algorithm von Hu, Shimin, Fong, Simon, Yang, Lili, Yang, Shuang-Hua, Dey, Nilanjan, Millham, Richard C., Fiaidhi, Jinan

“… Traditional data mining requires all the data to be available prior to inducing a model by supervised learning, for automatic image recognition or classification …”
Volltext

Parallel alternatives for evolutionary multi-objective optimization in unsupervised feature selection von Kimovski, Dragi, Ortega, Julio, Ortiz, Andrés, Baños, Raúl

“… Many machine learning and pattern recognition applications require reducing dimensionality to improve learning accuracy while irrelevant inputs are removed …”
Volltext

Increasing pattern recognition accuracy for chemical sensing by evolutionary based drift compensation von Di Carlo, S., Falasconi, M., Sanchez, E., Scionti, A., Squillero, G., Tonda, A.

“… Artificial olfaction systems, which mimic human olfaction by using arrays of gas chemical sensors combined with pattern recognition methods, represent a potentially low-cost tool in many areas …”
Volltext

Deep Optimisation: Transitioning the Scale of Evolutionary Search by Inducing and Searching in Deep Representations von Caldwell, Jamie, Knowles, Joshua, Thies, Christoph, Kubacki, Filip, Watson, Richard

“… We call the algorithm Deep Optimisation (DO) to recognise both its use of deep learning methods and the multi-level rescaling of biological evolutionary processes …”
Volltext

Deep learning improves macromolecule identification in 3D cellular cryo-electron tomograms von Moebel, Emmanuel, Martinez-Sanchez, Antonio, Lamm, Lorenz, Righetto, Ricardo D, Wietrzynski, Wojciech, Albert, Sahradha, Larivière, Damien, Fourmentin, Eric, Pfeffer, Stefan, Ortiz, Julio, Baumeister, Wolfgang, Peng, Tingying, Engel, Benjamin D, Kervrann, Charles

“… s. Once trained, the inference stage of DeepFinder is faster than template matching and performs better than other competitive deep learning methods at identifying macromolecules of various sizes …”
Volltext

ImaGene: a convolutional neural network to quantify natural selection from genomic data von Torada, Luis, Lorenzon, Lucrezia, Beddis, Alice, Isildak, Ulas, Pattini, Linda, Mathieson, Sara, Fumagalli, Matteo

“… An alternative approach to classic association studies to determining such genetic bases is an evolutionary framework …”
Volltext

SimilCatch: Enhanced social spammers detection on Twitter using Markov Random Fields von El-Mawass, Nour, Honeine, Paul, Vercouter, Laurent

“… highlights•Social spam evolution is leading to a marked deterioration in the performance of state-of-the-art supervised classifiers …”
Volltext

Fully automatic brain tumor segmentation with deep learning-based selective attention using overlapping patches and multi-class weighted cross-entropy von Ben naceur, Mostefa, Akil, Mohamed, Saouli, Rachida, Kachouri, Rostom

“… •A novel fully automatic Deep Convolutional Neural Networks model for brain tumor segmentation.•The model is inspired by the Occipito-Temporal Pathway …”
Volltext

Unsupervised visual feature learning with spike-timing-dependent plasticity: How far are we from traditional feature learning approaches? von Falez, Pierre, Tirilly, Pierre, Bilasco, Ioan Marius, Devienne, Philippe, Boulet, Pierre

“… •We compare the performance of spiking neural networks (SNNs) with auto-encoders for visual feature learning …”
Volltext

Self-adaptive attribute weighting for Naive Bayes classification von Wu, Jia, Pan, Shirui, Zhu, Xingquan, Cai, Zhihua, Zhang, Peng, Zhang, Chengqi

“… ) for attribute weighting.•Seamlessly integrating learning objective and AIS affinity function for attribute weighting …”
Volltext

Fully Automatic Brain Tumor Segmentation using End-To-End Incremental Deep Neural Networks in MRI images von naceur, Mostefa Ben, Saouli, Rachida, Akil, Mohamed, Kachouri, Rostom

“… •A new fully automatic end-to-end deep learning model for brain tumor segmentation …”
Volltext

Deep Representation-Based Feature Extraction and Recovering for Finger-Vein Verification von Qin, Huafeng, El-Yacoubi, Mounim A.

“… This paper proposes a deep learning model to extract and recover vein features using limited a priori knowledge …”
Volltext