A survey on multiview clustering
Clustering is a machine learning paradigm of dividing sample subjects into a number of
groups such that subjects in the same groups are more similar to those in other groups. With …
groups such that subjects in the same groups are more similar to those in other groups. With …
Predictive coding: a theoretical and experimental review
Predictive coding offers a potentially unifying account of cortical function--postulating that the
core function of the brain is to minimize prediction errors with respect to a generative model …
core function of the brain is to minimize prediction errors with respect to a generative model …
Three approaches for personalization with applications to federated learning
The standard objective in machine learning is to train a single model for all users. However,
in many learning scenarios, such as cloud computing and federated learning, it is possible …
in many learning scenarios, such as cloud computing and federated learning, it is possible …
Agnostic federated learning
A key learning scenario in large-scale applications is that of federated learning, where a
centralized model is trained based on data originating from a large number of clients. We …
centralized model is trained based on data originating from a large number of clients. We …
Center-based transfer feature learning with classifier adaptation for surface defect recognition
Y Shi, L Li, J Yang, Y Wang, S Hao - Mechanical Systems and Signal …, 2023 - Elsevier
Surface defect recognition using Deep Learning based computer vision techniques is an
important task in industrial manufacturing. However, surface images have different …
important task in industrial manufacturing. However, surface images have different …
Interpretable counterfactual explanations guided by prototypes
A Van Looveren, J Klaise - Joint European Conference on Machine …, 2021 - Springer
We propose a fast, model agnostic method for finding interpretable counterfactual
explanations of classifier predictions by using class prototypes. We show that class …
explanations of classifier predictions by using class prototypes. We show that class …
Fedboost: A communication-efficient algorithm for federated learning
Communication cost is often a bottleneck in federated learning and other client-based
distributed learning scenarios. To overcome this, several gradient compression and model …
distributed learning scenarios. To overcome this, several gradient compression and model …
Continual prototype evolution: Learning online from non-stationary data streams
Attaining prototypical features to represent class distributions is well established in
representation learning. However, learning prototypes online from streaming data proves a …
representation learning. However, learning prototypes online from streaming data proves a …
Prototypical networks for few-shot learning
Abstract We propose Prototypical Networks for the problem of few-shot classification, where
a classifier must generalize to new classes not seen in the training set, given only a small …
a classifier must generalize to new classes not seen in the training set, given only a small …
Optimized pre-processing for discrimination prevention
Non-discrimination is a recognized objective in algorithmic decision making. In this paper,
we introduce a novel probabilistic formulation of data pre-processing for reducing …
we introduce a novel probabilistic formulation of data pre-processing for reducing …