MLINFO COLLECTION
センサ時系列、画像検査、予測保全、異常スコアリングに使えるAI技術を整理します。
We study learning in continuous games when players receive only pairwise preference feedback, revealing which of two actions is preferred but neither payoff values nor preference magnitudes. We first…
A reliable assessment of an optimizer robustness requires tracking controlled changes in parameters to identify sources of algorithmic weakness. Such an approach was applied to the problem of…
Open-pit mining operational planning involves allocating limited resources while satisfying production, equipment, and ore-quality requirements. Existing approaches often assume deterministic ore…
A novel discovery is one which is both useful and surprising: a generative model's output is a useful discovery if it has a low probability of being generated (it's surprising) and a high reward…
Connectome models of the fly nerve cord generate walking-like motor rhythms, but oscillation alone does not show that the specific wiring matters. Here we provide, to our knowledge, the first test of…
We study the knowledge matrix of a trained feedforward network as a higher representation of its inputs. A network is a pair $(W,f)$, a thin representation $W$ of its quiver and an activation $f$;…
Spiking Vision Transformers (SViTs) are developed as an energy-efficient alternative to conventional ViTs for computer vision tasks at the edge. However, huge parameter counts and complex multi-head…
Most ANN-to-SNN conversion methods rely on a specific correspondence between the source activation and the spiking neuron dynamics. We propose a finite-state continuous-time Markov chain (CTMC)…
Physics-informed neural networks (PINNs) use one shared representation over the computational domain, which can become difficult to optimize on long domains and for high-order operators. We study a…
Many real-world optimization problems involve noisy objective evaluations and probabilistic constraints, particularly in the form of joint chance constraints, which are computationally expensive to…
A universal forecaster is trained once and applied everywhere, so it must serve tasks whose schemas, forecast horizons, and temporal resolutions all differ. The number of targets and covariates…
Margin bounds explain why weighted votes generalize after training error vanishes, but dependent observations require concentration arguments that keep the dependence model and failure budget…
We introduce two new methods for boundary detection in high-dimensional point cloud data, intended to work in situations with non-uniform density, high ambient dimension, and substantial noise. Our…
We consider the problem of online linear classification, where a stream of unlabeled samples is available, and annotation is costly. We investigate the optimal query policy, that prescribes whether…
Often, \emph{eg} in healthcare and predictive maintenance, what matters is which of several competing causes will strike first, and with what probability: survival analysis with competing risks.…
Can algorithms be learned and evolved as models, rather than repeatedly redesigned as programs? We explore this question by introducing Algorithm Modelization, a new paradigm that turns iterative…
On neuromorphic chips, spiking neural networks (SNNs) consume far less energy than artificial neural networks (ANNs), but the limited memory of these chips requires low-bit synaptic weights and…
Indivisible resources allocated in advance may need to be reallocated when capacity reductions make existing assignments infeasible, yet monetary compensation is often impractical or undesirable. We…
The linear representation hypothesis holds that pretrained vision models encode generative factors as linearly decodable directions in feature space, and comes with a standard methodology: train a…
Inferring dynamics from real-world experimental data is inherently ambiguous, as many plausible dynamical systems can explain the same positional observations at measurement times. For higher…
The input space of single-spike neural networks decomposes into causal pieces, and the number of causal pieces has been shown to provide a lower bound on the approximation error for some spiking…
Tabular foundation models based on prior-data fitted networks (PFNs) predict on a new data set in a single forward pass, but they cannot report which inputs their predictions depend on. We propose…
To facilitate the solving of complex problems, evolutionary multitask optimization is regarded as a promising technique due to its capacity for cross-task knowledge transfer. In contrast to empirical…
Spiking neural networks (SNNs) have increasingly incorporated rich neuronal dynamics to enhance temporal processing. However, richer dynamics do not necessarily enable neurons to adapt how…