scholarly journals Asymmetric Distribution Measure for Few-shot Learning

2020 ◽  
Author(s):  
Wenbin Li ◽  
Lei Wang ◽  
Jing Huo ◽  
Yinghuan Shi ◽  
Yang Gao ◽  
...  
Keyword(s):  
State Of The Art ◽  
Asymmetric Distribution ◽  
Query Image ◽  
Local Descriptor ◽  
Innovative Design ◽  
Feature Representations ◽  
The Core ◽  
Measure Function ◽  
Asymmetric Relation ◽  
Core Idea

The core idea of metric-based few-shot image classification is to directly measure the relations between query images and support classes to learn transferable feature embeddings. Previous work mainly focuses on image-level feature representations, which actually cannot effectively estimate a class's distribution due to the scarcity of samples. Some recent work shows that local descriptor based representations can achieve richer representations than image-level based representations. However, such works are still based on a less effective instance-level metric, especially a symmetric metric, to measure the relation between a query image and a support class. Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning. To that end, we propose a novel Asymmetric Distribution Measure (ADM) network for few-shot learning by calculating a joint local and global asymmetric measure between two multivariate local distributions of a query and a class. Moreover, a task-aware Contrastive Measure Strategy (CMS) is proposed to further enhance the measure function. On popular miniImageNet and tieredImageNet, ADM can achieve the state-of-the-art results, validating our innovative design of asymmetric distribution measures for few-shot learning. The source code can be downloaded from https://github.com/WenbinLee/ADM.git.

A New Hypervolume-based Evolutionary Algorithm for Many-objective Optimization

2020 ◽  
Author(s):  
Ke Shang ◽  
Hisao Ishibuchi
Keyword(s):  
Optimization Algorithm ◽  
State Of The Art ◽  
Experimental Studies ◽  
The Other ◽  
Tensor Structure ◽  
Multi Objective Optimization ◽  
Computationally Efficient ◽  
The Core ◽  
Core Idea ◽  
R2 Indicator

<div> <div> <div> <p>In this paper, a new hypervolume-based evolutionary multi-objective optimization algorithm (EMOA), namely R2HCA-EMOA (R2-based Hypervolume Contribution Approximation EMOA), is proposed for many-objective optimization. The core idea of the algorithm is to use an R2 indicator variant to approximate the hypervolume contribution. The basic framework of the proposed algorithm is the same as SMS- EMOA. In order to make the algorithm computationally efficient, a utility tensor structure is introduced for the calculation of the R2 indicator variant. Moreover, a normalization mechanism is incorporated into R2HCA-EMOA to enhance the performance of the algorithm. Through experimental studies, R2HCA-EMOA is compared with three hypervolume-based EMOAs and several other state-of-the-art EMOAs on 5-, 10- and 15-objective DTLZ, WFG problems and their minus versions. Our results show that R2HCA-EMOA is more efficient than the other hypervolume-based EMOAs, and is superior to all the compared state-of-the-art EMOAs. </p> </div> </div> </div>

scholarly journals A New Hypervolume-based Evolutionary Algorithm for Many-objective Optimization

2019 ◽  
Author(s):  
Ke Shang
Keyword(s):  
Optimization Algorithm ◽  
State Of The Art ◽  
Experimental Studies ◽  
The Other ◽  
Tensor Structure ◽  
Multi Objective Optimization ◽  
Computationally Efficient ◽  
The Core ◽  
Core Idea ◽  
R2 Indicator

<div> <div> <div> <p>In this paper, a new hypervolume-based evolution- ary multi-objective optimization algorithm (EMOA), namely R2HCA-EMOA (R2-based Hypervolume Contribution Approx- imation EMOA), is proposed for many-objective optimization. The core idea of the algorithm is to use an R2 indicator variant to approximate the hypervolume contribution. The basic framework of the proposed algorithm is the same as SMS- EMOA. In order to make the algorithm computationally efficient, a utility tensor structure is introduced for the calculation of the R2 indicator variant. Moreover, a normalization mechanism is incorporated into R2HCA-EMOA to enhance the performance of the algorithm. Through experimental studies, R2HCA-EMOA is compared with three hypervolume-based EMOAs and several other state-of-the-art EMOAs on 5-, 10- and 15-objective DTLZ, WFG problems and their minus versions. Our results show that R2HCA-EMOA is more efficient than the other hypervolume- based EMOAs, and is superior to all the compared state-of-the- art EMOAs. </p> </div> </div> </div>

scholarly journals Subgoaling Techniques for Satisficing and Optimal Numeric Planning

2020 ◽  
Vol 68 ◽  
pp. 691-752
Author(s):  
Enrico Scala ◽  
Patrik Haslum ◽  
Sylvie Thiébaux ◽  
Miquel Ramirez
Keyword(s):  
State Space ◽  
Heuristic Search ◽  
State Of The Art ◽  
Planning Problem ◽  
State Variables ◽  
The Core ◽  
State Space Search ◽  
Theoretical Assumptions ◽  
Good Trade ◽  
Core Idea

This paper studies novel subgoaling relaxations for automated planning with propositional and numeric state variables. Subgoaling relaxations address one source of complexity of the planning problem: the requirement to satisfy conditions simultaneously. The core idea is to relax this requirement by recursively decomposing conditions into atomic subgoals that are considered in isolation. Such relaxations are typically used for pruning, or as the basis for computing admissible or inadmissible heuristic estimates to guide optimal or satis_cing heuristic search planners. In the last decade or so, the subgoaling principle has underpinned the design of an abundance of relaxation-based heuristics whose formulations have greatly extended the reach of classical planning. This paper extends subgoaling relaxations to support numeric state variables and numeric conditions. We provide both theoretical and practical results, with the aim of reaching a good trade-o_ between accuracy and computation costs within a heuristic state-space search planner. Our experimental results validate the theoretical assumptions, and indicate that subgoaling substantially improves on the state of the art in optimal and satisficing numeric planning via forward state-space search.

scholarly journals PredCNN: Predictive Learning with Cascade Convolutions

2018 ◽  
Author(s):  
Ziru Xu ◽  
Yunbo Wang ◽  
Mingsheng Long ◽  
Jianmin Wang
Keyword(s):  
State Of The Art ◽  
Spatiotemporal Data ◽  
Challenging Problem ◽  
The Core ◽  
Predictive Learning ◽  
Flow Prediction ◽  
Video Frames ◽  
Memory Footprint ◽  
Core Idea ◽  
Video Prediction

Predicting future frames in videos remains an unsolved but challenging problem. Mainstream recurrent models suffer from huge memory usage and computation cost, while convolutional models are unable to effectively capture the temporal dependencies between consecutive video frames. To tackle this problem, we introduce an entirely CNN-based architecture, PredCNN, that models the dependencies between the next frame and the sequential video inputs. Inspired by the core idea of recurrent models that previous states have more transition operations than future states, we design a cascade multiplicative unit (CMU) that provides relatively more operations for previous video frames. This newly proposed unit enables PredCNN to predict future spatiotemporal data without any recurrent chain structures, which eases gradient propagation and enables a fully paralleled optimization. We show that PredCNN outperforms the state-of-the-art recurrent models for video prediction on the standard Moving MNIST dataset and two challenging crowd flow prediction datasets, and achieves a faster training speed and lower memory footprint.

scholarly journals A New Hypervolume-based Evolutionary Algorithm for Many-objective Optimization

2020 ◽  
Author(s):  
Ke Shang ◽  
Hisao Ishibuchi
Keyword(s):  
Optimization Algorithm ◽  
State Of The Art ◽  
Experimental Studies ◽  
The Other ◽  
Tensor Structure ◽  
Multi Objective Optimization ◽  
Computationally Efficient ◽  
The Core ◽  
Core Idea ◽  
R2 Indicator

<div> <div> <div> <p>In this paper, a new hypervolume-based evolutionary multi-objective optimization algorithm (EMOA), namely R2HCA-EMOA (R2-based Hypervolume Contribution Approximation EMOA), is proposed for many-objective optimization. The core idea of the algorithm is to use an R2 indicator variant to approximate the hypervolume contribution. The basic framework of the proposed algorithm is the same as SMS- EMOA. In order to make the algorithm computationally efficient, a utility tensor structure is introduced for the calculation of the R2 indicator variant. Moreover, a normalization mechanism is incorporated into R2HCA-EMOA to enhance the performance of the algorithm. Through experimental studies, R2HCA-EMOA is compared with three hypervolume-based EMOAs and several other state-of-the-art EMOAs on 5-, 10- and 15-objective DTLZ, WFG problems and their minus versions. Our results show that R2HCA-EMOA is more efficient than the other hypervolume-based EMOAs, and is superior to all the compared state-of-the-art EMOAs. </p> </div> </div> </div>

scholarly journals Adversarial Imitation Learning from Incomplete Demonstrations

2019 ◽  
Author(s):  
Mingfei Sun ◽  
Xiaojuan Ma
Keyword(s):  
State Of The Art ◽  
Auxiliary Information ◽  
The State ◽  
Imitation Learning ◽  
Action Sequence ◽  
State Information ◽  
The Core ◽  
Action Sequences ◽  
Core Idea ◽  
Novel Algorithm

Imitation learning targets deriving a mapping from states to actions, a.k.a. policy, from expert demonstrations. Existing methods for imitation learning typically require any actions in the demonstrations to be fully available, which is hard to ensure in real applications. Though algorithms for learning with unobservable actions have been proposed, they focus solely on state information and over- look the fact that the action sequence could still be partially available and provide useful information for policy deriving. In this paper, we propose a novel algorithm called Action-Guided Adversarial Imitation Learning (AGAIL) that learns a pol- icy from demonstrations with incomplete action sequences, i.e., incomplete demonstrations. The core idea of AGAIL is to separate demonstrations into state and action trajectories, and train a policy with state trajectories while using actions as auxiliary information to guide the training whenever applicable. Built upon the Generative Adversarial Imitation Learning, AGAIL has three components: a generator, a discriminator, and a guide. The generator learns a policy with rewards provided by the discriminator, which tries to distinguish state distributions between demonstrations and samples generated by the policy. The guide provides additional rewards to the generator when demonstrated actions for specific states are available. We com- pare AGAIL to other methods on benchmark tasks and show that AGAIL consistently delivers com- parable performance to the state-of-the-art methods even when the action sequence in demonstrations is only partially available.

Sustainable Development is a Dead-End: The Logic of Modernity and Ecological Crisis

2020 ◽  
Author(s):  
Simon Lumsden
Keyword(s):  
Sustainable Development ◽  
Ecological Crisis ◽  
Self Determination ◽  
Ecological Sustainability ◽  
Planetary Boundaries ◽  
Western Modernity ◽  
Conceptual Frame ◽  
The Core ◽  
Dead End ◽  
Core Idea

This paper examines the theory of sustainable development presented by Jeffrey Sachs in The Age of Sustainable Development. While Sustainable Development ostensibly seeks to harmonise the conflict between ecological sustainability and human development, the paper argues this is impossible because of the conceptual frame it employs. Rather than allowing for a re-conceptualisation of the human–nature relation, Sustainable Development is simply the latest and possibly last attempt to advance the core idea of western modernity — the notion of self-determination. Drawing upon Hegel’s account of historical development it is argued that Sustainable Development and the notion of planetary boundaries cannot break out of a dualism of nature and self-determining agents.

scholarly journals Representing Deep Neural Networks Latent Space Geometries with Graphs

Algorithms ◽  
2021 ◽  
Vol 14 (2) ◽  
pp. 39
Author(s):  
Carlos Lassance ◽  
Vincent Gripon ◽  
Antonio Ortega
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Objective Function ◽  
Learning Process ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
The Core ◽  
Learning Tasks ◽  
Latent Space

Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art performance in many machine learning tasks. The core principle of DL methods consists of training composite architectures in an end-to-end fashion, where inputs are associated with outputs trained to optimize an objective function. Because of their compositional nature, DL architectures naturally exhibit several intermediate representations of the inputs, which belong to so-called latent spaces. When treated individually, these intermediate representations are most of the time unconstrained during the learning process, as it is unclear which properties should be favored. However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought. In this work, we show that it is possible to introduce constraints on these latent geometries to address various problems. In more detail, we propose to represent geometries by constructing similarity graphs from the intermediate representations obtained when processing a batch of inputs. By constraining these Latent Geometry Graphs (LGGs), we address the three following problems: (i) reproducing the behavior of a teacher architecture is achieved by mimicking its geometry, (ii) designing efficient embeddings for classification is achieved by targeting specific geometries, and (iii) robustness to deviations on inputs is achieved via enforcing smooth variation of geometry between consecutive latent spaces. Using standard vision benchmarks, we demonstrate the ability of the proposed geometry-based methods in solving the considered problems.

scholarly journals Semi-Supervised Noisy Label Learning for Chinese Medical Named Entity Recognition

2021 ◽  
pp. 1-10
Author(s):  
Zhucong Li ◽  
Zhen Gan ◽  
Baoli Zhang ◽  
Yubo Chen ◽  
Jing Wan ◽  
...  
Keyword(s):  
Hybrid System ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Final Test ◽  
Named Entity ◽  
The Core ◽  
Category Labels ◽  
Adversarial Training ◽  
Core Idea ◽  
The Impact

Abstract This paper describes our approach for the Chinese Medical named entity recognition(MER) task organized by the 2020 China conference on knowledge graph and semantic computing(CCKS) competition. In this task, we need to identify the entity boundary and category labels of six entities from Chinese electronic medical record(EMR). We construct a hybrid system composed of a semi-supervised noisy label learning model based on adversarial training and a rule postprocessing module. The core idea of the hybrid system is to reduce the impact of data noise by optimizing the model results. Besides, we use post-processing rules to correct three cases of redundant labeling, missing labeling, and wrong labeling in the model prediction results. Our method proposed in this paper achieved strict criteria of 0.9156 and relax criteria of 0.9660 on the final test set, ranking first.

scholarly journals Unsupervised Deep Learning via Affinity Diffusion

2020 ◽  
Vol 34 (07) ◽  
pp. 11029-11036
Author(s):  
Jiabo Huang ◽  
Qi Dong ◽  
Shaogang Gong ◽  
Xiatian Zhu
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
General Purpose ◽  
Training Data ◽  
Learning Approach ◽  
Model Learning ◽  
Feature Representations ◽  
Discriminative Feature ◽  
Training Samples ◽  
Unsupervised Deep Learning

Convolutional neural networks (CNNs) have achieved unprecedented success in a variety of computer vision tasks. However, they usually rely on supervised model learning with the need for massive labelled training data, limiting dramatically their usability and deployability in real-world scenarios without any labelling budget. In this work, we introduce a general-purpose unsupervised deep learning approach to deriving discriminative feature representations. It is based on self-discovering semantically consistent groups of unlabelled training samples with the same class concepts through a progressive affinity diffusion process. Extensive experiments on object image classification and clustering show the performance superiority of the proposed method over the state-of-the-art unsupervised learning models using six common image recognition benchmarks including MNIST, SVHN, STL10, CIFAR10, CIFAR100 and ImageNet.

Sign in / Sign up

Export Citation Format

Share Document