Explore >> Select a destination

You are here

 proceedings.neurips.cc
On Adaptive Attacks to Adversarial Example Defenses
| | tomhume.org
Energy Efficiency drives Predictive Coding in Neural Networks | Tom Hume
12.8 parsecs away

Travel
| | I don't remember how I came across it, but this is one of the most exciting papers I've read recently. The authors train a neural network that tries to identify the next in a sequence of MNIST samples, presented in digit order. The interesting part is that when they include a proxy for energy usage in the loss function (i.e. train it to be more energy-efficient), the resulting network seems to exhibit the characteristics of predictive coding: some units seem to be responsible for predictions, others for encoding prediction error.
| | 0xa9f4.com
LLMs Spring 2023 | Jonathan Moore
13.1 parsecs away

Travel
| | LLMs and AI (Spring 2023) On March 14, 2023, GPT-4 was released, and the world entered a new era. Following this, there has been a frenzy of development in the AI space, with LLMs (Large Language Models) such as Alpaca, Bard, and many others.
| | nicholas.carlini.com
Are adversarial example defenses improving?
6.7 parsecs away

Travel
| | Abstract: We (again) broke a large collection of published defenses to adversarial examples. Here's how and why.
| | cstheory-events.org
LucaFest@Simons - CS Theory Events
59.8 parsecs away

Travel
| October 7-9, 2024 Simons Institute for the Theory of Computing, Berkeley, CA, USA https://simons.berkeley.edu/homepage There will be a workshop at the Simons Institute in Berkeley in celebration of the life and scientific contributions of the late Luca Trevisan (1971-2024). The workshop will be open to all who would like to attend, subject to capacity constraints....