Showing results 3331-3340 of >3,403 (page 334)
https://papers.nips.cc/paper/2020/hash/417fbbf2e9d5a28a855a11894b2e795a-Abstract.html

NeurIPS Proceedings Search Evaluating Attribution for Graph Neural Networks Benjamin Sanchez-Lengeling, Jennifer Wei, Brian Lee, Emily Reif, Peter Wang, Wesley Qian, Kevin McCloskey, Lucy Colwell, Alexander Wiltschko Advances in Neural Information Processing Systems 33 (NeurIPS 2020) Abstract Interpretability of machine learning models is critical to scientific understanding, AI safety, as well as debugging. Attribution is one approach to interpretability, which highlights input dimensions that are influent

https://www.hyperbots.com/glossary/probabilistic-neural-network

Learn how Probabilistic Neural Networks analyze financial data using probability models to improve forecasting, risk analysis, and business performance

https://www.schneier.com/blog/archives/2020/06/availability_at.html

## Availability Attacks against Neural Networks New research on using specially crafted inputs to slow down machine-learning neural network systems: Sponge Examples: Energy-Latency Attacks on Neural Networks shows how to find adversarial examples that cause a DNN to burn more energy, take more time, or both. They affect a wide range of DNN applications, from image recognition to natural language processing (NLP). Adversaries might use these examples for all sorts of mischief—from draining mobile phone bat

https://towardsdatascience.com/neural-network-from-tenet-exploiting-time-inversion-fdc512f5fec3/

Modelling dynamical systems with recurrent neural networks

https://thegradient.pub/shortcuts-neural-networks-love-to-cheat/

On unifying many of deep learning’s problems and with the concepts of "shortcuts", and what we can do to better understand and mitigate shortcut learning.

https://chapelle.cc/machine-learning-neural-research/

Look, I have watched neural networks go from academic toys to the engines of the global economy. But power without proof is just a liability. That is why this

https://philosophy-science-humanities-controversies.com/listview-list.php?concept=Artificial+Neural+Networks

Comparison of theories - Pros and cons - Aristotle - Brandom - Chalmers - Dennett - Epicurus - Foucault - Grice - Habermas - Kripke - Locke - Mill - Quine

https://www.isca-archive.org/interspeech_2015/lin15_interspeech.html

ISCA Archive Interspeech 2015 ISCA Archive Interspeech 2015 Speech recognition with temporal neural networks Payton Lin, Dau-Cheng Lyu, Yun-Fan Chang, Yu Tsao Raw temporal features were derived from extracted temporal envelope bank (referred to as “Tbank”). Tbank features were used with deep neural networks (DNNs) to greatly increase the amount of detailed information about the past to be carried forward to help in the interpretation of the future. @inproceedings{lin15_interspeech, title = {{Speech

https://moldstud.com/articles/p-key-considerations-for-integrating-activation-functions-in-neural-networks-a-guide-for-developers

Selecting an appropriate activation function is crucial for enhancing neural network performance Includes practical examples and decisions for key considerations

https://www.emergentmind.com/topics/slimmable-networks

Slimmable Networks enable a single neural model to operate at multiple widths, balancing accuracy and efficiency through adaptive channel activation and separate normalization

‹ Prev Next ›