Lifeboat Foundation: Safeguarding Humanity
Toggle light / dark theme

Blog

Category: robotics/AI – Page 704

Wav-KAN: Wavelet Kolmogorov-Arnold Networks

The codes to replicate the simulations of the paper: Available at: https://arxiv.org/abs/2405.12832 and also: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4835325

For now, we just added the codes to…

In this paper, we introduce Wav-KAN, an innovative neural network architecture that leverages the Wavelet Kolmogorov-Arnold Networks (Wav-KAN) framework to enhance interpretability and performance. Traditional multilayer perceptrons (MLPs) and even recent advancements like Spl-KAN \cite{kan} face challenges related to interpretability, training speed, robustness, computational efficiency, and performance. Wav-KAN addresses these limitations by incorporating wavelet functions into the Kolmogorov-Arnold network structure, enabling the network to capture both high-frequency and low-frequency components of the input data efficiently. Wavelet-based approximations employ orthogonal or semi-orthogonal basis and also maintains a balance between accurately representing the underlying data structure and avoiding overfitting to the noise. Analogous to how water conforms to the shape of its container, Wav-KAN adapts to the data structure, resulting in enhanced accuracy, faster training speeds, and increased robustness compared to Spl-KAN and MLPs. Our results highlight the potential of Wav-KAN as a powerful tool for developing interpretable and high-performance neural networks, with applications spanning various fields. This work sets the stage for further exploration and implementation of Wav-KAN in frameworks such as PyTorch, TensorFlow, and also it makes wavelet in KAN in wide-spread usage like nowadays activation functions like ReLU, sigmoid in universal approximation theory (UAT).

The DOJ makes its first known arrest for AI-generated CSAM

The US Department of Justice arrested a Wisconsin man last week for generating and distributing AI-generated child sexual abuse material (CSAM). As far as we know, this is the first case of its kind as the DOJ looks to establish a judicial precedent that exploitative materials are still illegal even when no children were used to create them. “Put simply, CSAM generated by AI is still CSAM,” Deputy Attorney General Lisa Monaco wrote in a press release.

The DOJ says 42-year-old software engineer Steven Anderegg of Holmen, WI, used a fork of the open-source AI image generator Stable Diffusion to make the images, which he then used to try to lure an underage boy into sexual situations. The latter will likely play a central role in the eventual trial for the four counts of “producing, distributing, and possessing obscene visual depictions of minors engaged in sexually explicit conduct and transferring obscene material to a minor under the age of 16.”

The government says Anderegg’s images showed “nude or partially clothed minors lasciviously displaying or touching their genitals or engaging in sexual intercourse with men.” The DOJ claims he used specific prompts, including negative prompts (extra guidance for the AI model, telling it what not to produce) to spur the generator into making the CSAM.

Project Astra demo | Solving math problems

Watch Project Astra factorise a maths problem and even correct a graph. All shot on a prototype glasses device, in a single take in real time.

Project Astra is a prototype that explores the future of AI assistants. Building on our Gemini models, we’ve developed AI agents that can quickly process multimodal information, reason about the context you’re in, and respond to questions at a conversational pace, making interactions feel much more natural.

More about Project Astra: deepmind.google/project-astra

AI Outperforms Humans in Theory of Mind Tests

Theory of mind —the ability to understand other people’s mental states—is what makes the social world of humans go around. It’s what helps you decide what to say in a tense situation, guess what drivers in other cars are about to do, and empathize with a character in a movie. And according to a new study, the large language models (LLM) that power ChatGPT and the like are surprisingly good at mimicking this quintessentially human trait.

“Before running the study, we were all convinced that large language models would not pass these tests, especially tests that evaluate subtle abilities to evaluate mental states,” says study coauthor Cristina Becchio, a professor of cognitive neuroscience at the University Medical Center Hamburg-Eppendorf in Germany. The results, which she calls “unexpected and surprising,” were published today —somewhat ironically, in the journal Nature Human Behavior.

The results don’t have everyone convinced that we’ve entered a new era of machines that think like we do, however. Two experts who reviewed the findings advised taking them “with a grain of salt” and cautioned about drawing conclusions on a topic that can create “hype and panic in the public.” Another outside expert warned of the dangers of anthropomorphizing software programs.

/* */