Showing results 4961-4970 of >5,032 (page 497)
https://kourentzes.com/forecasting/2011/04/19/modelling-functional-outliers-for-high-frequency-time-series-forecasting-with-neural-networks-an-empirical-evaluation-for-electricity-load-data/

Nikolaos Kourentzes Forecasting research Skip to content Downloads About Modelling functional outliers for high frequency time series forecasting with neural networks: an empirical evaluation for electricity load data By Nikos | April 19, 2011 0 Comment N. Kourentzes, 2011, International Conference on Data Mining, DMIN’2011, Las Vegas, 18-21 July 2011. This paper discusses and empirically evaluates alternative methodologies in modeling functional outliers for high frequency time series forecasting. In

https://www.emergentmind.com/papers/2101.07600

Exploratory analysis of time series data can yield a better understanding of complex dynamical systems. Granger causality is a practical framework for analysing interactions in sequential data, applied in a wide range of domains. In this paper, we propose a novel framework for inferring multivariate Granger causality under nonlinear dynamics based on an extension of self-explaining neural networks. This framework is more interpretable than other neural-network-based techniques for inferring Granger causalit

https://dzone.com/articles/Neural-Network-Representations

In this article, explore an in-depth introduction to mechanistic interpretability and neural network representations

http://jmlr.org/beta/papers/v23/21-0368.html

--> Approximation and Optimization Theory for Linear Continuous-Time Recurrent Neural Networks Zhong Li, Jiequn Han, Weinan E, Qianxiao Li. Year: 2022, Volume: 23 , Issue: 42, Pages: 1−85 Abstract We perform a systematic study of the approximation properties and optimization dynamics of recurrent neural networks (RNNs) when applied to learn input-output relationships in temporal data. We consider the simple but representative setting of using continuous-time linear RNNs to learn from data generated by

https://danmackinlay.name/notebook/nn_conv.html

Wherein Convolutional Neural Networks Are Presented as a Topology Whose Layers Are Constructed With Finite-Impulse-Response Filters and Pooling, Receptive Fields Are Computed for Analysis, and Activations Are Visualised as High-Rank Tensors With Exploitable Regularity

https://impetora.com/glossary/neural-network

A neural network is a computational model loosely inspired by biological neurons, in which weighted connections between simple units learn to map inputs to outputs

https://victorzhou.com/blog/intro-to-neural-networks/

A simple explanation of how they work and how to implement one from scratch in Python.

https://www.capitalone.com/tech/open-source/open-source-global-attribution-mapping-for-neural-networks/

To assess potential model bias and understand overall model behavior, global explanations of predictions are used. Learn more from Capital One's findings.

https://www.purebytes.com/archives/omega/2002/msg09156.html

Re: Are the Neural Networks and Fuzzy logic of any use ?, Omega TradeStation Email Archive, PureBytes.Com

https://curatedsql.com/2020/12/02/logistic-regression-as-a-neural-network/

Press "Enter" to skip to content Curated SQL A Fine Slice Of SQL Server open menu Search About Logistic Regression as a Neural Network Published 2020-12-02 by Kevin Feasel Holger von Jouanne-Diedrich takes us through ways in which we can understand certain types of neural networks from the lens of logistic regression : We already covered Neural Networks and Logistic Regression in this blog. If you want to gain an even deeper understanding of the fascinating connection between those two popular machine learn

‹ Prev Next ›