paper-with-me

홈 › Papers

What are Neural Networks made of?

2019-08-25 · Rene Schaub

The success of Deep Learning methods is not well understood, though various attempts at explaining it have been made, typically centered on properties of stochastic gradient descent. Even less clear is why certain neural network architectures perform better than others. We provide a potential opening with the hypothesis that neural network training is a form of Genetic Programming.

📄 PDF Abstract BibTeX arXiv:1909.09588

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Teaching and Critiquing Conceptualization and Operationalization in NLP

2025-12-20 · Vagrant Gautam arxiv

NLP researchers regularly invoke abstract concepts like "interpretability," "bias," "reasoning," and "stereotypes," without defining them. Each subfield has a shared understanding or conceptualization of what these terms…

Coexistence of two dengue virus serotypes and forecasting for Madeira island

2015-07-15

The first outbreak of dengue occurred in Madeira Island on 2012, featuring one virus serotype. Aedes aegypti was the vector of the disease and it is unlikely that it will be eliminated from the island. Therefore, a new o…

Vocal Bursts Valence Prediction

A theory of appropriateness with applications to generative artificial intelligence

2024-12-26 · Joel Z. Leibo, Alexander Sasha Vezhnevets, Manfred Diaz, John P. Agapiou 외

What is appropriateness? Humans navigate a multi-scale mosaic of interlocking notions of what is appropriate for different situations. We act one way with our friends, another with our family, and yet another in the offi…

Decision MakingNavigate

What if we knew what the future brings? Optimal investment for a frontrunner with price impact

2021-08-09 · Peter Bank, Yan Dolinsky, Miklós Rásonyi

In this paper we study optimal investment when the investor can peek some time units into the future, but cannot fully take advantage of this knowledge because of quadratic transaction costs. In the Bachelier setting wit…

What Taggers Fail to Learn, Parsers Need the Most

2021-04-02 · NoDaLiDa 2021 5 · Mark Anderson, Carlos Gómez-Rodríguez

We present an error analysis of neural UPOS taggers to evaluate why using gold standard tags has such a large positive contribution to parsing performance while using predicted UPOS tags either harms performance or offer…