Zobrazeno 1 - 10
of 810
pro vyhledávání: '"Alper T."'
Autor:
Alper T. Güven
Publikováno v:
International Journal of Preventive Medicine, Vol 15, Iss 1, Pp 7-7 (2024)
Externí odkaz:
https://doaj.org/article/c0f26a017873496da792cb88327b59c0
The backpropagation algorithm has experienced remarkable success in training large-scale artificial neural networks; however, its biological plausibility has been strongly criticized, and it remains an open question whether the brain employs supervis
Externí odkaz:
http://arxiv.org/abs/2306.04810
Autor:
Tatli, Gokcan, Erdogan, Alper T.
We introduce a Bayesian perspective for the structured matrix factorization problem. The proposed framework provides a probabilistic interpretation for existing geometric methods based on determinant minimization. We model input data vectors as linea
Externí odkaz:
http://arxiv.org/abs/2302.08416
The brain effortlessly extracts latent causes of stimuli, but how it does this at the network level remains unknown. Most prior attempts at this problem proposed neural networks that implement independent component analysis which works under the limi
Externí odkaz:
http://arxiv.org/abs/2210.04222
Extraction of latent sources of complex stimuli is critical for making sense of the world. While the brain solves this blind source separation (BSS) problem continuously, its algorithms remain unknown. Previous work on biologically-plausible BSS algo
Externí odkaz:
http://arxiv.org/abs/2209.12894
Self-supervised learning allows AI systems to learn effective representations from large amounts of data using tasks that do not require costly labeling. Mode collapse, i.e., the model producing identical representations for all inputs, is a central
Externí odkaz:
http://arxiv.org/abs/2209.07999
Autor:
Erdogan, Alper T.
Publikováno v:
2022 IEEE Conference on Acoustics, Speech and Signal Processing
We introduce a new information maximization (infomax) approach for the blind source separation problem. The proposed framework provides an information-theoretic perspective for determinant maximization-based structured matrix factorization methods su
Externí odkaz:
http://arxiv.org/abs/2205.00794
Autor:
Bozkurt, Bariscan, Erdogan, Alper T.
Polytopic matrix factorization (PMF) is a recently introduced matrix decomposition method in which the data vectors are modeled as linear transformations of samples from a polytope. The successful recovery of the original factors in the generative PM
Externí odkaz:
http://arxiv.org/abs/2204.11534
Autor:
Tatli, Gokcan, Erdogan, Alper T.
Publikováno v:
IEEE Transactions on Signal Processing 2021
We introduce Polytopic Matrix Factorization (PMF) as a novel data decomposition approach. In this new framework, we model input data as unknown linear transformations of some latent vectors drawn from a polytope. In this sense, the article considers
Externí odkaz:
http://arxiv.org/abs/2202.09638