Results 11 to 20 of about 448,167 (282)
Algorithms, 2022 Universal adversarial attacks, which hinder most deep neural network (DNN) tasks using only a single perturbation called universal adversarial perturbation (UAP), are a realistic security threat to the practical application of a DNN for medical imaging ...
Kazuki Koga, Kazuhiro Takemoto
doaj +1 more source
Combining white box models, black box machines and human interventions for interpretable decision strategies [PDF]
Judgment and Decision Making, 2022 Granting a short-term loan is a critical decision. A great deal of research has concerned the prediction of credit default, notably through Machine Learning (ML) algorithms.
Gregory Gadzinski, Alessio Castello
doaj +2 more sources
Fast Black-Box Quantum State Preparation [PDF]
Quantum, 2022 Quantum state preparation is an important ingredient for other higher-level quantum algorithms, such as Hamiltonian simulation, or for loading distributions into a quantum device to be used e.g.
Johannes Bausch
doaj +1 more source
NECSUS, 2023 This article argues that the critical study of algorithms must shift its focus from solving the problem of the ‘black box’ to seeing the structures that surround and pose it as a problematic in the first place.
Leo Hansson Nilson
doaj +1 more source
Mathematics, 2023 In order to overcome the drawbacks of expensive function evaluation in the practical reliability-based design optimization (RBDO) problem, researchers have proposed the black box-based RBDO method.
Li Lu, Yizhong Wu, Qi Zhang, Ping Qiao
doaj +1 more source
Using Black-Box Compression Algorithms for Phase Retrieval [PDF]
IEEE Transactions on Information Theory, 2020 Compressive phase retrieval refers to the problem of recovering a structured $n$-dimensional complex-valued vector from its phase-less under-determined linear measurements. The non-linearity of measurements makes designing theoretically-analyzable efficient phase retrieval algorithms challenging.
Milad Bakhshizadeh +2 more
openaire +2 more sources
The politics of algorithmic governance in the black box city [PDF]
Big Data & Society, 2020 Everyday surveillance work is increasingly performed by non-human algorithms. These entities can be conceptualised as machinic flâneurs that engage in distanciated flânerie: subjecting urban flows to a dispassionate, calculative and expansive gaze.
openaire +2 more sources
Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics [PDF]
, 2018 The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model ...
Chatzilygeroudis, Konstantinos +1 more
core +2 more sources
Better fixed-arity unbiased black-box algorithms [PDF]
Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2018 An extended abstract will appear at GECCO ...
Nina Bulanova, Maxim Buzdalov 0001
openaire +2 more sources
Applied Sciences, 2023 Over the past few decades, machine learning has emerged as a valuable tool in the field of medicine, driven by the accumulation of vast amounts of medical data and the imperative to harness this data for the betterment of humanity.
Bojan Žlahtič +5 more
doaj +1 more source