Related papers: Imposing Connectome-Derived Topology on an Echo St…
Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency. We introduce Efficient Selective Language Modeling (ESLM), a risk-aware algorithm that improves training…
Thompson sampling (TS) is a popular heuristic for action selection, but it requires sampling from a posterior distribution. Unfortunately, this can become computationally intractable in complex environments, such as those modeled using…
The El Ni\~{n}o-Southern Oscillation (ENSO) is a dominant mode of interannual climate variability, yet the mechanisms limiting its long-lead predictability remain unclear. Here we develop a physics-guided Deep Echo State Network (DESN) that…
Federated Learning deviates from the norm of "send data to model" to "send model to data". When used in an edge ecosystem, numerous heterogeneous edge devices collecting data through different means and connected through different network…
Classical artificial neural networks have witnessed widespread successes in machine-learning applications. Here, we propose fermion neural networks (FNNs) whose physical properties, such as local density of states or conditional…
The mushroom body is the key network for the representation of learned olfactory stimuli in Drosophila and insects. The sparse activity of Kenyon cells, the principal neurons in the mushroom body, plays a key role in the learned…
The echo state network (ESN) is a special type of recurrent neural networks for processing the time-series dataset. However, limited by the strong correlation among sequential samples of the agent, ESN-based policy control algorithms are…
We present a novel approach to EEG decoding for non-invasive brain machine interfaces (BMIs), with a focus on motor-behavior classification. While conventional convolutional architectures such as EEGNet and DeepConvNet are effective in…
To solve high-dimensional parameter-dependent partial differential equations (pPDEs), a neural network architecture is presented. It is constructed to map parameters of the model data to corresponding finite element solutions. To improve…
Modeling the behavior of coupled networks is challenging due to their intricate dynamics. For example in neuroscience, it is of critical importance to understand the relationship between the functional neural processes and anatomical…
Stock return prediction is a problem that has received much attention in the finance literature. In recent years, sophisticated machine learning methods have been shown to perform significantly better than ''classical'' prediction…
Modern vision generators transport a base distribution to data through time-indexed measures, implemented as deterministic flows (ODEs) or stochastic diffusions (SDEs). Despite strong empirical performance, standard flow-matching objectives…
While existing predictive frameworks are able to handle Euclidean structured data (i.e, brain images), they might fail to generalize to geometric non-Euclidean data such as brain networks. Besides, these are rooted the sample selection step…
Underwater acoustic (UWA) communications have been widely used but greatly impaired due to the complicated nature of the underwater environment. In order to improve UWA communications, modeling and understanding the UWA channel is…
Many machine learning tasks can be expressed as the transformation---or \emph{transduction}---of input sequences into output sequences: speech recognition, machine translation, protein secondary structure prediction and text-to-speech to…
Efficiently identifying the right trajectories for training remains an open problem in GFlowNets. To address this, it is essential to prioritize exploration in regions of the state space where the reward distribution has not been…
Brain connectomes offer detailed maps of neural connections within the brain. Recent studies have proposed novel connectome graph datasets and attempted to improve connectome classification by using graph deep learning. With recent advances…
Solving flow through porous media is a crucial step in the topology optimisation of cold plates, a key component in modern thermal management. Traditional computational fluid dynamics (CFD) methods, while accurate, are often prohibitively…
Elementary net systems (ENS) are the most fundamental class of Petri nets. Their synthesis problem has important applications in the design of digital hardware and commercial processes. Given a labeled transition system (TS) $A$,…
Modern large-scale machine learning applications require stochastic optimization algorithms to be implemented on distributed compute systems. A key bottleneck of such systems is the communication overhead for exchanging information across…