Results 241 to 250 of about 1,307,610 (290)

Performance–Complexity Trade‐Offs in Battery Lifetime Prediction with Task‐Aware Transformers

Advanced Science, EarlyView.
FAST‐BatPro integrates convolutional feature extraction, flash Attention, and sparse attention for efficient battery lifetime prediction. Using limited early‐cycle data across multiple chemistries and operating conditions, it achieves robust accuracy while reducing inference latency, computational cost, and energy consumption.
Jingyuan Zhao, Misheng Cai, Zhenghong Wang, Yan Wang, Yuqi Li, Bo Dong, Hewu Wang, Andrew F. Burke, Simona Onori, Stephen J. Harris   +9 more
wiley   +1 more source

Social Status and Clinical Resource Allocation by a Large Language Model: An Evaluation of 30,618 Decisions. [PDF]

J Pers Med
Gandhi S, Balas M.
europepmc   +1 more source

The Algorithmic Regulator. [PDF]

Entropy (Basel)
Ruffini G.
europepmc   +1 more source

Reframing the starting point of shared decision-making under algorithmic short-form video exposure: bone tumor care as a sentinel context. [PDF]

Front Public Health
Wang JW, Feng YF, Zhang ZB.
europepmc   +1 more source

The impact of transparency and imitation over complex networks in strategic classification. [PDF]

PLoS One
Barsotti F, Santos FP.
europepmc   +1 more source

Multi-task adversarial learning detects intersectional algorithmic bias in AI recruitment systems. [PDF]

Sci Rep
Wang J, Xu Y, Liu R, Du Y.
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

UNIVERSAL ALGORITHMS FOR PROBABILITY FORECASTING

International Journal on Artificial Intelligence Tools, 2012
Multi-class classification is one of the most important tasks in machine learning. In this paper we consider two online multi-class classification problems: classification by a linear model and by a kernelized model. The quality of predictions is measured by the Brier loss function. We obtain two computationally efficient algorithms for these problems
Fedor Zhdanov, Yuri Kalnishkan
openaire   +8 more sources

Algorithms and Probabilities

2014
This chapter accomplishes two goals. First, it introduces a number of algorithms of a probabilistic nature. For this, it starts with a discussion of random number generators and related functions, followed by algorithms for shuffling a collection of objects, selecting a fair sample from a collection, and simulating a probabilistic event.
Dana Vrajitoru, William Knight
openaire   +1 more source

Bounds on the Performance of a Greedy Algorithm for Probabilities

Mathematics of Operations Research, 2001
A bound on the performance of the greedy algorithm for finding the maximum of a submodular set function subject to a cardinality constraint is shown to apply to the problem of selecting a fixed number of events so that the probability that at least one of the selected events occurs is maximized.
John C. Gittins, Gavin Harper
openaire   +3 more sources

An algorithm for approximating conditional probabilities

International Journal of Bio-Medical Computing, 1990
When diagnostic programs are constructed within a probabilistic framework, it is often the case that computation of joint probabilities of exhaustive combinations of events is easy, but computation of the kind of conditional probabilities the user wishes to know, is hard.
openaire   +2 more sources