Neurological disorders that affect speech production, such as Alzheimer's Disease (AD), significantly impact the lives of both patients and caregivers, whether through social, psycho-emotional effects or other aspects not yet fully understood. Recent...
We develop and analyze MARINA: a new communication efficient method for non-convex distributed learning over heterogeneous datasets. MARINA employs a novel communication compression strategy based on the compression of gradient differences that is re...
To address the distribution shifts between training and test data, domain generalization (DG) leverages multiple source domains to learn a model that generalizes well to unseen domains. However, existing DG methods generally suffer from overfitting t...
Deep neural networks often produce overconfident predictions, undermining their reliability in safety-critical applications. This miscalibration is further exacerbated under distribution shift, where test data deviates from the training distribution...
A fundamental problem in supervised learning is to find a good set of features or distance measures. If the new set of features is of lower dimensionality and can be obtained by a simple transformation of the original data, they can make the model un...
This paper presents a gradient based motion estimation algorithm based on shape-motion prediction, which takes advantage of the correlation between neighboring Binary Alpha Blocks (BABs), to match with the Mpeg-4 shape coding case and speed up the...
Data selection for instruction tuning is crucial for improving the performance of large language models (LLMs) while reducing training costs. In this paper, we propose Refined Contribution Measurement with In-Context Learning (RICo), a novel gradient...
Elements of neural networks, both biological and artificial, can be described by their selectivity for specific cognitive features. Understanding these features is important for understanding the inner workings of neural networks. For a living system...
The magnetic field which induced by the thermo-electric current in metals was detected and measured using of a flux-gate magnetometer. It is shown that the application of a temperature gradient on a metal rod gives rise to a circulating current there...
We re-estimate the angular 2-point galaxy correlation function from the Lick galaxy catalogue. We argue that the large-scale gradients observed in the Lick catalogue are dominated by real clustering and therefore they should not be subtracted prior...
The effectiveness of deep residual networks hinges on the identity shortcut connection. While this mechanism alleviates the vanishing-gradient problem, it also has a strictly additive inductive bias on feature transformations, limiting the network's...
Fine-tuning-as-a-service introduces a threat to Large Language Models' safety when service providers fine-tune their models on poisoned user-submitted datasets, a process known as harmful fine-tuning attacks. In this work, we show that by regularizin...
Gold clusters Aun of size n = 2 to 12 atoms were studied by the density-functional theory with an ab-initio pseudopotential and a generalized gradient approximation. Geometry optimizations starting from a number of initial candidate geometries were...
Modeling the transport dynamics of natural processes from population-level observations is a ubiquitous problem in the natural sciences. Such models rely on key assumptions about the underlying process in order to enable faithful learning of governin...
Adversarial attacks have become a significant challenge in the security of machine learning models, particularly in the context of black-box defense strategies. Existing methods for enhancing adversarial transferability primarily focus on the spatial...
Variational quantum algorithms use non-convex optimization methods to find the optimal parameters for a parametrized quantum circuit in order to solve a computational problem. The choice of the circuit ansatz, which consists of parameterized gates, i...
Human fingers achieve exceptional dexterity and adaptability by combining structures with varying stiffness levels, from soft tissues (low) to tendons and cartilage (medium) to bones (high). This paper explores developing a robotic finger with simila...
Random Recurrent Neural Networks (RRNN) are the simplest recurrent networks to model and extract features from sequential data. The simplicity however comes with a price; RRNN are known to be susceptible to diminishing/exploding gradient problem when...
We introduce Hyper-Trees as a novel framework for modeling time series data using gradient boosted trees. Unlike conventional tree-based approaches that forecast time series directly, Hyper-Trees learn the parameters of a target time series model, su...
Read in a gradient from a png file and spit out CSS for it (⭐ 257)