Lifeboat Foundation

Deep Learning (DL) has shown great promise in the unsupervised task of clustering. That said, while in classical (i.e., non-deep) clustering the benefits of the nonparametric approach are well known, most deep-clustering methods are parametric: namely, they require a predefined and fixed number of clusters, denoted by K. When K is unknown, however, using model-selection criteria to choose its optimal value might become computationally expensive, especially in DL as the training process would have to be repeated numerous times. In this work, we bridge this gap by introducing an effective deep-clustering method that does not require knowing the value of K as it infers it during the learning. Using a split/merge framework, a dynamic architecture that adapts to the changing K, and a novel loss, our proposed method outperforms existing nonparametric methods (both classical and deep ones).

Note: This is a joint distillation of both Iterated Distillation and Amplification by Ajeya Cotra (summarizing Paul Christiano) and A Generalist Agent by DeepMind.

Oscillations are widespread throughout the natural world and a number of fascinating inorganic oscillating reactions are known—but the formation and control of oscillating, self-replicating synthetic systems has remained challenging. Now, it has been shown that chemically fuelled oscillations within a network of organic replicators can drive supramolecular assembly and disassembly.

“The Price of Immortality” is a balanced and fluent account of the diverse movement to make humans immortal https://econ.trib.al/wGM2Vwu

Credit: Murray Ballard.

New laws are meant to prevent espionage and leaking.

If you are interested in artificial general intelligence (AGI), then I have a panel discussion to recommend. My friend, David Wood, has done a masterful job of selecting three panelists with deep insight into possible regulation of AGI. One of the panelists was my friend, Dan Faggella, who was eloquent and informative as usual. For this session of the London Futurists, David Wood selected two other panelists with significantly different opinions on how to properly restrain AGI.

An artificial general intelligence (AGI), by one definition, is an agent that requires less information than any other to make an accurate prediction. It is arguable that the general reinforcement learning agent AIXI not only met this definition, but was the only mathematical formalism to do so. Though a significant result, AIXI was incomputable and its performance subjective. This paper proposes an alternative formalism of AGI which overcomes both problems. Formal proof of its performance is given, along with a simple implementation and experimental results that support these claims.

Here are some things I would expect any AGI to be able to do:…

Epistemic status: trying to feel out the shape of a concept and give it an appropriate name. Trying to make explicit some things that I think exist implicitly in many people’s minds. This post makes truth claims, but its main goal is to not to convince you that they are true.

One of the biggest challenges in a World Building competition that asked teams to imagine a positive future with superintelligent AI: Make it plausible.

Today we’re going to shine some light on Lumen, the fully dynamic global illumination and reflections system featured in Unreal Engine 5.

Our latest tech blog… See more.

Continue reading “Unreal Engine 5 goes all-in on dynamic global illumination with Lumen” »