Unsupervised Feature Learning With Winner-Takes-All Based STDP
نویسندگان
چکیده
منابع مشابه
Unsupervised Feature Learning With Winner-Takes-All Based STDP
We present a novel strategy for unsupervised feature learning in image applications inspired by the Spike-Timing-Dependent-Plasticity (STDP) biological learning rule. We show equivalence between rank order coding Leaky-Integrate-and-Fire neurons and ReLU artificial neurons when applied to non-temporal data. We apply this to images using rank-order coding, which allows us to perform a full netwo...
متن کاملWinner-Takes-All based Multi-Strategy Learning for Information Extraction
The proliferation of information on the Internet has enabled one find any information he/she is looking for. Nevertheless, almost all of these informations are designed for human readers and are not machine readable. Information extraction is a task that addresses the above problem by extracting a piece of information from unstructured formats. This paper proposes a winner-takes-all based multi...
متن کاملThe winner takes it all.
W e all make mistakes from time to time. I have made my fair share, but none of my mistakes have ever won a prize. In 2002 Lundbeck breached the UK industry code of practice in the way it advertised escitalopram (Cipralex). Escitalopram is the son of citalopram (Cipramil). The company claimed that its new drug, escitalopram was more effective than citalopram, even though the two drugs have exac...
متن کاملThe winner takes it all
We study competing first passage percolation on graphs generated by the configuration model. At time 0, vertex 1 and vertex 2 are infected with the type 1 and the type 2 infection, respectively, and an uninfected vertex then becomes type 1 (2) infected at rate λ1 (λ2) times the number of edges connecting it to a type 1 (2) infected neighbor. Our main result is that, if the degree distribution i...
متن کاملLearning vector quantization: The dynamics of winner-takes-all algorithms
Winner-Takes-All (WTA) prescriptions for Learning Vector Quantization (LVQ) are studied in the framework of a model situation: Two competing prototype vectors are updated according to a sequence of example data drawn from a mixture of Gaussians. The theory of on-line learning allows for an exact mathematical description of the training dynamics, even if an underlying cost function cannot be ide...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Frontiers in Computational Neuroscience
سال: 2018
ISSN: 1662-5188
DOI: 10.3389/fncom.2018.00024