scholarly journals Improving Learning-from-Crowds through Expert Validation

2017 ◽  
Author(s):  
Mengchen Liu ◽  
Liu Jiang ◽  
Junlin Liu ◽  
Xiting Wang ◽  
Jun Zhu ◽  
...  
Keyword(s):  
Bayesian Inference ◽  
Supervised Learning ◽  
Real World ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Uncertainty Assessment ◽  
Effective Learning ◽  
Complete Uncertainty ◽  
Expert Validation ◽  
Selection Of

Although several effective learning-from-crowd methods have been developed to infer correct labels from noisy crowdsourced labels, a method for post-processed expert validation is still needed. This paper introduces a semi-supervised learning algorithm that is capable of selecting the most informative instances and maximizing the influence of expert labels. Specifically, we have developed a complete uncertainty assessment to facilitate the selection of the most informative instances. The expert labels are then propagated to similar instances via regularized Bayesian inference. Experiments on both real-world and simulated datasets indicate that given a specific accuracy goal (e.g., 95%) our method reduces expert effort from 39% to 60% compared with the state-of-the-art method.

scholarly journals DDPG Agent to Swing Up and Balance Cart- Pole System

2021 ◽  
pp. 102-116
Author(s):  
Buvanesh Pandian V
Keyword(s):  
Reinforcement Learning ◽  
Supervised Learning ◽  
Real World ◽  
Learning Algorithm ◽  
Current Approach ◽  
Control Problems ◽  
Mathematical Framework ◽  
Test Environment ◽  
Continuous Action ◽  
Action Spaces

Reinforcement learning is a mathematical framework for agents to interact intelligently with their environment. Unlike supervised learning, where a system learns with the help of labeled data, reinforcement learning agents learn how to act by trial and error only receiving a reward signal from their environments. A field where reinforcement learning has been prominently successful is robotics [3]. However, real-world control problems are also particularly challenging because of the noise and high- dimensionality of input data (e.g., visual input). In recent years, in the field of supervised learning, deep neural networks have been successfully used to extract meaning from this kind of data. Building on these advances, deep reinforcement learning was used to solve complex problems like Atari games and Go. Mnih et al. [1] built a system with fixed hyper parameters able to learn to play 49 different Atari games only from raw pixel inputs. However, in order to apply the same methods to real-world control problems, deep reinforcement learning has to be able to deal with continuous action spaces. Discretizing continuous action spaces would scale poorly, since the number of discrete actions grows exponentially with the dimensionality of the action. Furthermore, having a parametrized policy can be advantageous because it can generalize in the action space. Therefore with this thesis we study state-of-the-art deep reinforcement learning algorithm, Deep Deterministic Policy Gradients. We provide a theoretical comparison to other popular methods, an evaluation of its performance, identify its limitations and investigate future directions of research. The remainder of the thesis is organized as follows. We start by introducing the field of interest, machine learning, focusing our attention of deep learning and reinforcement learning. We continue by describing in details the two main algorithms, core of this study, namely Deep Q-Network (DQN) and Deep Deterministic Policy Gradients (DDPG). We then provide implementatory details of DDPG and our test environment, followed by a description of benchmark test cases. Finally, we discuss the results of our evaluation, identifying limitations of the current approach and proposing future avenues of research.

scholarly journals Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels with Variational Auto-Encoder

2021 ◽  
Author(s):  
Weijia Zhang
Keyword(s):  
Medical Imaging ◽  
Supervised Learning ◽  
Real World ◽  
State Of The Art ◽  
Experimental Results ◽  
Weakly Supervised Learning ◽  
Variational Autoencoder ◽  
Label Prediction ◽  
Weakly Supervised ◽  
Better Than

Multi-instance learning is a type of weakly supervised learning. It deals with tasks where the data is a set of bags and each bag is a set of instances. Only the bag labels are observed whereas the labels for the instances are unknown. An important advantage of multi-instance learning is that by representing objects as a bag of instances, it is able to preserve the inherent dependencies among parts of the objects. Unfortunately, most existing algorithms assume all instances to be identically and independently distributed, which violates real-world scenarios since the instances within a bag are rarely independent. In this work, we propose the Multi-Instance Variational Autoencoder (MIVAE) algorithm which explicitly models the dependencies among the instances for predicting both bag labels and instance labels. Experimental results on several multi-instance benchmarks and end-to-end medical imaging datasets demonstrate that MIVAE performs better than state-of-the-art algorithms for both instance label and bag label prediction tasks.

scholarly journals Co-GCN for Multi-View Semi-Supervised Learning

2020 ◽  
Vol 34 (04) ◽  
pp. 4691-4698
Author(s):  
Shu Li ◽  
Wen-Tao Li ◽  
Wei Wang
Keyword(s):  
Supervised Learning ◽  
Real World ◽  
State Of The Art ◽  
Data Sets ◽  
Real World Data ◽  
Convolutional Network ◽  
The Past ◽  
Real World Applications ◽  
Supervised Methods ◽  
Disjoint Sets

In many real-world applications, the data have several disjoint sets of features and each set is called as a view. Researchers have developed many multi-view learning methods in the past decade. In this paper, we bring Graph Convolutional Network (GCN) into multi-view learning and propose a novel multi-view semi-supervised learning method Co-GCN by adaptively exploiting the graph information from the multiple views with combined Laplacians. Experimental results on real-world data sets verify that Co-GCN can achieve better performance compared with state-of-the-art multi-view semi-supervised methods.

scholarly journals Active Selection of Label Data for Semi-Supervised Learning Algorithm

2013 ◽  
Vol 17 (3) ◽  
pp. 254-259 ◽  
Author(s):  
Ji-Ho Han ◽  
Eun-Ae Park ◽  
Dong-Chul Park ◽  
Yunsik Lee ◽  
Soo-Young Min
Keyword(s):  
Supervised Learning ◽  
Learning Algorithm ◽  
Label Data ◽  
Active Selection ◽  
Selection Of

scholarly journals Artificial Intelligence-Based Network Selection and Optimized Routing in Internet of Vehicles

2021 ◽  
Vol 22 (4) ◽  
pp. 392-406
Author(s):  
Shaik Mazhar Hussain ◽  
Kamaludin Mohamad Yusof ◽  
Shaik Ashfaq Hussain
Keyword(s):  
Performance Metrics ◽  
Road Traffic ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Vertical Handover ◽  
Traffic Information ◽  
Internet Of Vehicles ◽  
Radio Access ◽  
4G Lte ◽  
Selection Of

Abstract Internet of Vehicles (IoV) is a network of vehicles communicating with each other by exchanging road traffic information via radio access technologies. Two potential technologies of V2X that have gained attention over the past years are DSRC and cellular networks such as 4G LTE and 5G. DSRC is suitable for low latency communications, however provides a shorter coverage range whereas, 4G LTE offers a wide coverage range but has high transmission time intervals. In contrast, 5G offers higher data rates, low latencies but prone to blockages. Single technology might not fully accommodate the requirements of vehicular communications. Hence, it is required to interwork with more than one radio access network to satisfy the requirements of safety vehicular applications. One issue identified when working with multiple radio access networks is the selection of the most appropriate network for vertical handover. Usually, in the previous works, the network is selected directly or will be connected to the available network due to which the handover had to take place frequently resulting in unnecessary handovers. Hence, in the existing state-of-the-art, the need for handover is not validated. In this paper, we have proposed a dynamic Q-learning algorithm to validate the need for handover, and then, appropriate selection of network would take place by using a fuzzy convolutional neural network. Besides, a modified jellyfish optimization algorithm is proposed to select the shortest paths by forming V2V pairs that take into account channel metrics, vehicle metrics, and vehicle performance metrics. The proposed algorithms are then evaluated using OMNET++ and compared with the existing state-of-the-art concerning mean handover, HO failure, throughput, delay, and packet loss as the performance metrics.

scholarly journals Partial Label Learning with Batch Label Correction

2020 ◽  
Vol 34 (04) ◽  
pp. 6575-6582
Author(s):  
Yan Yan ◽  
Yuhong Guo
Keyword(s):  
Real World ◽  
Data Augmentation ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Learning Problem ◽  
True Label ◽  
Network Update ◽  
The Stability ◽  
Partial Label Learning ◽  
Noisy Labels

Partial label (PL) learning tackles the problem where each training instance is associated with a set of candidate labels, among which only one is the true label. In this paper, we propose a simple but effective batch-based partial label learning algorithm named PL-BLC, which tackles the partial label learning problem with batch-wise label correction (BLC). PL-BLC dynamically corrects the label confidence matrix of each training batch based on the current prediction network, and adopts a MixUp data augmentation scheme to enhance the underlying true labels against the redundant noisy labels. In addition, it introduces a teacher model through a consistency cost to ensure the stability of the batch-based prediction network update. Extensive experiments are conducted on synthesized and real-world partial label learning datasets, while the proposed approach demonstrates the state-of-the-art performance for partial label learning.

scholarly journals That’s Mine! Learning Ownership Relations and Norms for Robots

2019 ◽  
Vol 33 ◽  
pp. 8058-8065 ◽  
Author(s):  
Zhi-Xuan Tan ◽  
Jake Brawer ◽  
Brian Scassellati
Keyword(s):  
Bayesian Inference ◽  
Social Norms ◽  
Recent Work ◽  
Real World ◽  
Autonomous Agents ◽  
Learning Algorithm ◽  
Future Research ◽  
Social Environments ◽  
Social Rules ◽  
Exploratory Stage

The ability for autonomous agents to learn and conform to human norms is crucial for their safety and effectiveness in social environments. While recent work has led to frameworks for the representation and inference of simple social rules, research into norm learning remains at an exploratory stage. Here, we present a robotic system capable of representing, learning, and inferring ownership relations and norms. Ownership is represented as a graph of probabilistic relations between objects and their owners, along with a database of predicate-based norms that constrain the actions permissible on owned objects. To learn these norms and relations, our system integrates (i) a novel incremental norm learning algorithm capable of both one-shot learning and induction from specific examples, (ii) Bayesian inference of ownership relations in response to apparent rule violations, and (iii) perceptbased prediction of an object’s likely owners. Through a series of simulated and real-world experiments, we demonstrate the competence and flexibility of the system in performing object manipulation tasks that require a variety of norms to be followed, laying the groundwork for future research into the acquisition and application of social norms.

Classification and Recognition of Electronic Components Based on Improved Cooperative Semi-supervised Learning Algorithm

2020 ◽  
Vol 14 ◽  
Author(s):  
Dan Luo
Keyword(s):  
Deep Learning ◽  
Machine Vision ◽  
Supervised Learning ◽  
Image Recognition ◽  
Production Efficiency ◽  
Learning Algorithm ◽  
Electronic Components ◽  
Electron Device ◽  
Actual Recognition ◽  
The Subject

Background: As known that the semi-supervised algorithm is a classical algorithm in semi-supervised learning algorithm. Methods: In the paper, it proposed improved cooperative semi-supervised learning algorithm, and the algorithm process is presented in detailed, and it is adopted to predict unlabeled electronic components image. Results: In the experiments of classification and recognition of electronic components, it show that through the method the accuracy the proposed algorithm in electron device image recognition can be significantly improved, the improved algorithm can be used in the actual recognition process . Conclusion: With the continuous development of science and technology, machine vision and deep learning will play a more important role in people's life in the future. The subject research based on the identification of the number of components is bound to develop towards the direction of high precision and multi-dimension, which will greatly improve the production efficiency of electronic components industry.

scholarly journals Improving Semi-Supervised Learning for Audio Classification with FixMatch

Electronics ◽  
2021 ◽  
Vol 10 (15) ◽  
pp. 1807
Author(s):  
Sascha Grollmisch ◽  
Estefanía Cano
Keyword(s):  
Neural Networks ◽  
Supervised Learning ◽  
Transfer Learning ◽  
Data Transfer ◽  
State Of The Art ◽  
Training Data ◽  
Audio Classification ◽  
Image Domain ◽  
Full Dataset ◽  
Audio Data

Including unlabeled data in the training process of neural networks using Semi-Supervised Learning (SSL) has shown impressive results in the image domain, where state-of-the-art results were obtained with only a fraction of the labeled data. The commonality between recent SSL methods is that they strongly rely on the augmentation of unannotated data. This is vastly unexplored for audio data. In this work, SSL using the state-of-the-art FixMatch approach is evaluated on three audio classification tasks, including music, industrial sounds, and acoustic scenes. The performance of FixMatch is compared to Convolutional Neural Networks (CNN) trained from scratch, Transfer Learning, and SSL using the Mean Teacher approach. Additionally, a simple yet effective approach for selecting suitable augmentation methods for FixMatch is introduced. FixMatch with the proposed modifications always outperformed Mean Teacher and the CNNs trained from scratch. For the industrial sounds and music datasets, the CNN baseline performance using the full dataset was reached with less than 5% of the initial training data, demonstrating the potential of recent SSL methods for audio data. Transfer Learning outperformed FixMatch only for the most challenging dataset from acoustic scene classification, showing that there is still room for improvement.

scholarly journals Deep Learning Classification of Canine Behavior Using a Single Collar-Mounted Accelerometer: Real-World Validation

Animals ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1549
Author(s):  
Robert D. Chambers ◽  
Nathanael C. Yoder ◽  
Aletha B. Carson ◽  
Christian Junge ◽  
David E. Allen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Real World ◽  
Learning Algorithm ◽  
Drinking Behavior ◽  
True Positive Rate ◽  
Training Dataset ◽  
Activity Levels ◽  
Accelerometer Data ◽  
Activity Monitors

Collar-mounted canine activity monitors can use accelerometer data to estimate dog activity levels, step counts, and distance traveled. With recent advances in machine learning and embedded computing, much more nuanced and accurate behavior classification has become possible, giving these affordable consumer devices the potential to improve the efficiency and effectiveness of pet healthcare. Here, we describe a novel deep learning algorithm that classifies dog behavior at sub-second resolution using commercial pet activity monitors. We built machine learning training databases from more than 5000 videos of more than 2500 dogs and ran the algorithms in production on more than 11 million days of device data. We then surveyed project participants representing 10,550 dogs, which provided 163,110 event responses to validate real-world detection of eating and drinking behavior. The resultant algorithm displayed a sensitivity and specificity for detecting drinking behavior (0.949 and 0.999, respectively) and eating behavior (0.988, 0.983). We also demonstrated detection of licking (0.772, 0.990), petting (0.305, 0.991), rubbing (0.729, 0.996), scratching (0.870, 0.997), and sniffing (0.610, 0.968). We show that the devices’ position on the collar had no measurable impact on performance. In production, users reported a true positive rate of 95.3% for eating (among 1514 users), and of 94.9% for drinking (among 1491 users). The study demonstrates the accurate detection of important health-related canine behaviors using a collar-mounted accelerometer. We trained and validated our algorithms on a large and realistic training dataset, and we assessed and confirmed accuracy in production via user validation.

Sign in / Sign up

Export Citation Format

Share Document