Neural Information Processing Systems http://nips.cc/

Graphcodes handle datasets that are filtered along two real-valued scale parameters.

The Sliced Wasserstein Kernel (SWK) for persistence diagrams was introduced in (Carri{è}re et al. 2017) as a powerful tool to implicitly embed persistence diagrams in a Hilbert space with reasonable distortion. This kernel is built on the intuition that the Figalli-Gigli distance-that is the partial matching distance routinely used to compare persistence diagrams-resembles the Wasserstein distance used in the optimal transport literature, and that the later could be sliced to define a positive definite kernel on the space of persistence diagrams. This efficient construction nonetheless relies on ad-hoc tweaks on the Wasserstein distance to account for the peculiar geometry of the space of persistence diagrams. In this work, we propose to revisit this idea by directly using the Figalli-Gigli distance instead of the Wasserstein one as the building block of our kernel. On the theoretical side, our sliced Figalli-Gigli kernel (SFGK) shares most of the important properties of the SWK of Carri{è}re et al., including distortion results on the induced embedding and its ease of computation, while being more faithful to the natural geometry of persistence diagrams. In particular, it can be directly used to handle infinite persistence diagrams and persistence measures. On the numerical side, we show that the SFGK performs as well as the SWK on benchmark applications.

For a given set of points, define a value called "weight" for each point in (a),

For Taro Ueno, a psychiatrist and president of Susmed, the idea to develop an app for insomnia came from observing how doctors in Japan overprescribe sleeping pills. Japan's medical industry has generally been slow to embrace digital technology, with many clinics still keeping patient records and writing prescriptions on paper. But a few domestic startups have recently launched chatbot-powered apps designed to help treat a range of conditions, such as hypertension, alcohol addiction and insomnia. Unlike the plethora of lifestyle apps anyone with a smartphone can download, these are prescription-only medical apps whose efficacy has been demonstrated in clinical trials. For Taro Ueno, a psychiatrist and brain researcher, the idea to develop an app for insomnia came from observing how doctors in Japan overprescribe sleeping pills. In a time of both misinformation and too much information, quality journalism is more crucial than ever.

Grok, a chatbot developed by xAI, has faced criticism for churning out incorrect information about recent crises. Washington - Elon Musk's AI tool Grok faced growing international backlash Monday for generating sexualized deepfakes of women and minors, with the European Union joining the condemnation and Britain warning of an investigation. Complaints of abuse flooded the internet after the recent rollout of an "edit image" button on Grok, which enabled users to alter online images with prompts such as "put her in a bikini" or "remove her clothes." The digital undressing spree, which follows growing concerns among tech campaigners over proliferating AI "nudify" apps, prompted swift probes or calls for remedial action from countries including France, India and Malaysia. In a time of both misinformation and too much information, quality journalism is more crucial than ever. By subscribing, you can help us get the story right.

Topological data analysis (TDA) has been used successfully in a wide array of applications, for instance in medical (Nicolau et al., 2011) or material (Hiraoka et al., 2016) sciences, computer vision (Li et al., 2014) or to classify NBA players (Lum et al., 2013).

Machine learning based on neural networks has advanced rapidly, but the high energy consumption required for training and inference remains a major challenge. Hyperdimensional Computing (HDC) offers a lightweight, brain-inspired alternative that enables high parallelism but often suffers from lower accuracy on complex visual tasks. To overcome this, hybrid accelerators combining HDC and Convolutional Neural Networks (CNNs) have been proposed, though their adoption is limited by poor generalizability and programmability. The rise of open-source RISC-V architectures has created new opportunities for domain-specific GPU design. Unlike traditional proprietary GPUs, emerging RISC-V-based GPUs provide flexible, programmable platforms suitable for custom computation models such as HDC. In this study, we design and implement custom GPU instructions optimized for HDC operations, enabling efficient processing for hybrid HDC-CNN workloads. Experimental results using four types of custom HDC instructions show a performance improvement of up to 56.2 times in microbenchmark tests, demonstrating the potential of RISC-V GPUs for energy-efficient, high-performance computing.