Results 11 to 20 of about 476,790 (313)

Representation Learning by Learning to Count [PDF]

2017 IEEE International Conference on Computer Vision (ICCV), 2017
We introduce a novel method for representation learning that uses an artificial supervision signal based on count- ing visual primitives. This supervision signal is obtained from an equivariance relation, which does not require any manual annotation.
Noroozi, Mehdi, Favaro, Paolo, Pirsiavash, Hamed   +2 more
core   +3 more sources

Graph Representation Learning [PDF]

ESANN 2023 proceesdings, 2023
In a broad range of real-world machine learning applications, representing examples as graphs is crucial to avoid a loss of information. Due to this in the last few years, the definition of machine learning methods, particularly neural networks, for ...
Bacciu, Davide, Alessio Micheli, Navarin, Nicolò, Federico Errica, Luca Pasa, Nicolo Navarin, Zambon, Daniele, Daniele Zambon, Micheli, Alessio, Podda, Marco, Errica, Federico, Marco Podda, Pasa, Luca, Davide Bacciu   +13 more
core   +4 more sources

Deep Representation Learning for Speech Emotion Recognition [PDF]

, 2022
The success of machine learning (ML) algorithms generally depends on the quality of data representation or features. Good representations of the data make it easier to develop machine learning predictors or even deep learning (DL) classifiers.
Latif, Siddique
core   +1 more source

Survey of deep representation learning for speech emotion recognition [PDF]

, 2023
Traditionally, speech emotion recognition (SER) research has relied on manually handcrafted acoustic features using feature engineering. However, the design of handcrafted features for complex SER tasks requires significant manual eort, which impedes ...
Siddique Latif, Latif, Siddique, Sara Khalifa, Rajib Rana, Raja Jurdak, Junaid Qadir, Rana, Rajib, Qadir, Junaid, Schuller, Bjorn, Schuller, Björn W., Khalifa, Sara, Jurdak, Raja, Björn Schuller   +12 more
core   +1 more source

Challenges in representation learning: A report on three machine learning contests

, 2022
S.59-63The ICML 2013 Workshop on Challenges in Representation Learning [http://deeplearning.net/icml2013-workshop-competition] focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal ...
Erhan, Dumitru, Carrier, Pierre Luc, Athanasakis, Dimitris, Goodfellow, Ian J., Lee, Dong-Hyun, Zhou, Yingbo, Tang, Yichuan, Hamner, Ben, Li, Ruifan, Wang, Xiaojie, Milakov, Maxim, Cukierski, Will, Xie, Jingjing, Thaler, David, Courville, Aaron, Bergstra, James, Xu, Bing, Chuang, Zhang, Feng, Fangxiang, Ramaiah, Chetan, Ionescu, Radu, Romaszko, Lukasz, Shawe-Taylor, John, Park, John, Popescu, Marius, Grozea, Cristian, Mirza, Mehdi, Bengio, Yoshua   +27 more
core   +2 more sources

Learning Overcomplete Representations [PDF]

Neural Computation, 2000
In an overcomplete basis, the number of basis vectors is greater than the dimensionality of the input, and the representation of an input is not a unique combination of basis vectors. Overcomplete representations have been advocated because they have greater robustness in the presence of noise, can be sparser, and can have greater flexibility in ...
Michael S. Lewicki, Terrence J. Sejnowski   +1 more
openaire   +2 more sources

Deep boundary‑aware clustering by jointly optimizing unsupervised representation learning [PDF]

, 2022
Deep clustering obtains feature representation generally and then performs clustering for high dimension real-world data. However, conventional solutions are two-stage embedding learning-based methods and these two processes are separate and independent,
Li, Lin, Liu, Peiyu, Tao, Xiaohui, Wang, Peipei, Wang, Ru   +4 more
core   +1 more source

Learning with Probabilistic Representations [PDF]

Machine Learning, 1997
1. Introduction and motivationMachine learning cannot occur without some means to represent the learned knowledge.Researchers have long recognized the influence of representational choices, and the majorparadigms in machine learning are organized not around induction algorithms or perfor-manceelementsasmuchasaroundrepresentationalclasses ...
Pat Langley, Gregory M. Provan, Padhraic Smyth   +2 more
openaire   +1 more source

Mathematical Representation Ability of Students on Linear Program Material in Terms of Learning Interests in Problem Based Learning

Journal of Medives: Journal of Mathematics Education IKIP Veteran Semarang, 2023
This study aims to determine the completeness of the implementation of Problem-Based Learning (PBL) to the achievement of students' mathematical representation skills, determine the influence of learning interest on the mathematical representation ...
Safa Agrita Hilsania, Masrukan Masrukan
doaj   +1 more source

Roy-lab/graph-representation-learning: v1.1

, 2023
Source Code and Supplementary Materials for Paper "Benchmarking graph representation learning algorithms for detecting modules in molecular networks"
zsong96wisc, Sushmita Roy
core   +1 more source