arXiv:2601.17110v1 Announce Type: new Abstract: Accurate short-term energy consumption forecasting is essential for efficient power grid management, resource allocation, and market stability. Traditional time-series models often fail to capture the complex, non-linear dependencies and external factors affecting energy demand. In this study, we propose a forecasting approach based on Recurrent Neural Networks (RNNs) and their advanced variant, Long Short-Term Memory (LSTM) networks. Our methodology integrates historical energy consumption data with external variables, including temperature, humidity, and time-based features. […]

Ver mais

For most of human history, writing was slow, scarce, and authoritative. To write was to fix meaning in place, and to read was to accept that fixation as a serious act. Digital networks loosened that authority by making text cheap and abundant. Generative AI finishes the job by removing human effort as the primary constraint on producing words. Once that happens, writing can no longer derive its value from the act of production itself. Its value must come […]

Ver mais

Over several decades, I unlearned everything that I learned in college classes, and built a new discipline from scratch, as much different from traditional AI than it is from standard machine learning, statistics and computer science. Outside academia with a focus on practical applications. Item #2 in the list below is the culmination of this research. In the meanwhile, other tech founders just use what they or their team learned at Stanford or Google Labs, with little twists. […]

Ver mais

Equivariant neural networks exploit underlying task symmetries to improve generalization, but strict equivariance constraints can induce more complex optimization dynamics that can hinder learning. Prior work addresses these limitations by relaxing strict equivariance during training, but typically relies on prespecified, explicit, or implicit target levels of relaxation for each network layer, which are task-dependent and costly to tune. We propose Recurrent Equivariant Constraint Modulation (RECM), a layer-wise constraint modulation mechanism that learns appropriate relaxation levels solely from the […]

Ver mais

arXiv:2601.20901v1 Announce Type: new Abstract: With LLMs increasingly deployed in corporate data management, it is crucial to ensure that these models do not leak sensitive information. In the context of corporate data management, the concept of sensitivity awareness has been introduced, enabling LLMs to adhere to predefined access rights rules. However, it remains unclear how sensitivity awareness relates to established notions of privacy, such as differential privacy (DP), thereby making it difficult to deploy meaningfully in real-world applications. […]

Ver mais

Machine learning approaches for fringe projection profilometry (FPP) are hindered by the lack of large, diverse datasets and comprehensive benchmarking protocols. This paper introduces the first open-source, photorealistic synthetic dataset for FPP, generated using NVIDIA Isaac Sim with 15,600 fringe images and 300 depth reconstructions across 50 diverse objects. We benchmark four neural network architectures (UNet, Hformer, ResUNet, Pix2Pix) on single-shot depth reconstruction, revealing that all models achieve similar performance (58-77 mm RMSE) despite substantial architectural differences. Our […]

Ver mais

I’m taking a break from my series on celestial navigation. The previous posts give the basics, but I haven’t thought of a way to go further that I’m satisfied with. So now for something completely different: Pedersen commitments. Pedersen commitments are a building block of zero knowledge proofs (ZKP), and they give an opportunity to look at a couple other interesting topics: nothing-up-my-sleeve constructions and homomorphic encryption. A Pedersen commitment to a value v takes a random number x […]

Ver mais

arXiv:2602.10303v1 Announce Type: cross Abstract: Predicting time-to-event outcomes when event times are interval censored is challenging because the exact event time is unobserved. Many existing survival analysis approaches for interval-censored data rely on strong model assumptions or cannot handle high-dimensional predictors. We develop ICODEN, an ordinary differential equation-based neural network for interval-censored data that models the hazard function through deep neural networks and obtains the cumulative hazard by solving an ordinary differential equation. ICODEN does not require the […]

Ver mais

Across the financial technology sector, large institutions are facing a hard reality. Systems that were built decades ago for stability and control are now under pressure to deliver flexibility, cost efficiency, and faster change. Banks and market infrastructure firms continue to depend on legacy data centers to process sensitive trade data, where outages and errors are not an option. Yet rising operational costs and growing demand for agility have made cloud adoption less of a future goal and […]

Ver mais