Results 51 to 60 of about 114,287 (303)
CoRR, 2020 Irrespective of the specific definition of fairness in a machine learning application, pruning the underlying model affects it. We investigate and document the emergence and exacerbation of undesirable per-class performance imbalances, across tasks and architectures, for almost one million categories considered across over 100K image classification ...
openaire +2 more sources
Pruning and measures of uncertainty [PDF]
RAIRO. Informatique théorique, 1978 We introduce a new property, pruning, for measures of uncertainty and investigate its consequences. In particular, we derive a new characterization of the additive, subadditive and symmetric entropies without assuming expansibility. Pruning also provides a new motivation for Hartley's entropy.
B. Forte, SEMPI, Carlo
openaire +4 more sources
Dimension-Based Subscription Pruning for Publish/Subscribe Systems
, 2006 Subscription pruning has been proven as valuable routing optimization for Boolean subscriptions in publish/ subscribe systems. It aims at optimizing subscriptions independently of each other and is thus applicable for all kinds of subscriptions ...
Bittner, Sven +3 more
core +1 more source
Merging pruning and neuroevolution: towards robust and efficient controllers for modular soft robots [PDF]
, 2022 Artificial neural networks (ANNs) can be employed as controllers for robotic agents. Their structure is often complex, with many neurons and connections, especially when the robots have many sensors and actuators distributed across their bodies and/or ...
Pellegrino, Felice Andrea +6 more
core +1 more source
Life-cycle assessment of the use of peach pruning residues for electricity generation [PDF]
, 2020 Biomass residues from permanent crops might be an alternative fuel for energy generation in a local market with limited transport distances. Moreover, as activities related to CO2 reduction are of special attention in the European Union (EU), sustainable
Boer, E.D. +11 more
core +1 more source
Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks [PDF]
International Joint Conference on Artificial Intelligence, 2018 This paper proposed a Soft Filter Pruning (SFP) method to accelerate the inference procedure of deep Convolutional Neural Networks (CNNs). Specifically, the proposed SFP enables the pruned filters to be updated when training the model after pruning.
Yang He +4 more
semanticscholar +1 more source
White Matter Microstructural Abnormalities in Neonatal Onset Genetic Epilepsy
Annals of Clinical and Translational Neurology, EarlyView.ABSTRACT Objective Recent evidence indicates that epilepsy is associated with abnormal white matter. If seizures alter white matter, then the impact upon network function, epileptogenesis, and cognition could be pronounced in neonates undergoing rapid developmental myelination. Neonates with epilepsy due to nonstructural genetic causes provide a unique
Amanda G. Sandoval Karamian +8 more
wiley +1 more source
Implementing Agricultural Pruning to Energy in Europe: Technical, Economic and Implementation Potentials [PDF]
, 2019 The use of new sources of biomass residues for energy purposes in Europe is crucial for increasing the share of renewable energy sources and the limitation of carbon dioxide emissions.
Daniel García-Galindo +3 more
core +1 more source
Importance Estimation for Neural Network Pruning [PDF]
Computer Vision and Pattern Recognition, 2019 Structural pruning of neural network parameters reduces computational, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those with
Pavlo Molchanov +4 more
semanticscholar +1 more source
International Journal of Approximate Reasoning, 2018 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Eunice Yuh-Jie Chen +2 more
openaire +4 more sources