scholarly journals Perturbation Training for Human-Robot Teams

2017 ◽  
Vol 59 ◽  
pp. 495-541 ◽  
Author(s):  
Ramya Ramakrishnan ◽  
Chongjie Zhang ◽  
Julie Shah
Keyword(s):  
Transfer Learning ◽  
Large Scale ◽  
Communication Protocol ◽  
Learning Algorithm ◽  
Training Strategy ◽  
Learning Framework ◽  
Perturbation Training ◽  
Learning Techniques ◽  
High Level ◽  
Live Interaction

In this work, we design and evaluate a computational learning model that enables a human-robot team to co-develop joint strategies for performing novel tasks that require coordination. The joint strategies are learned through "perturbation training," a human team-training strategy that requires team members to practice variations of a given task to help their team generalize to new variants of that task. We formally define the problem of human-robot perturbation training and develop and evaluate the first end-to-end framework for such training, which incorporates a multi-agent transfer learning algorithm, human-robot co-learning framework and communication protocol. Our transfer learning algorithm, Adaptive Perturbation Training (AdaPT), is a hybrid of transfer and reinforcement learning techniques that learns quickly and robustly for new task variants. We empirically validate the benefits of AdaPT through comparison to other hybrid reinforcement and transfer learning techniques aimed at transferring knowledge from multiple source tasks to a single target task. We also demonstrate that AdaPT's rapid learning supports live interaction between a person and a robot, during which the human-robot team trains to achieve a high level of performance for new task variants. We augment AdaPT with a co-learning framework and a computational bi-directional communication protocol so that the robot can co-train with a person during live interaction. Results from large-scale human subject experiments (n=48) indicate that AdaPT enables an agent to learn in a manner compatible with a human's own learning process, and that a robot undergoing perturbation training with a human results in a high level of team performance. Finally, we demonstrate that human-robot training using AdaPT in a simulation environment produces effective performance for a team incorporating an embodied robot partner.

scholarly journals Mol-BERT: An Effective Molecular Representation with BERT for Molecular Property Prediction

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Juncai Li ◽  
Xiaofei Jiang
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Large Scale ◽  
Molecular Data ◽  
Molecular Property ◽  
Property Prediction ◽  
Learning Framework ◽  
Learning Techniques ◽  
Potential Benefits ◽  
Current Sequence

Molecular property prediction is an essential task in drug discovery. Most computational approaches with deep learning techniques either focus on designing novel molecular representation or combining with some advanced models together. However, researchers pay fewer attention to the potential benefits in massive unlabeled molecular data (e.g., ZINC). This task becomes increasingly challenging owing to the limitation of the scale of labeled data. Motivated by the recent advancements of pretrained models in natural language processing, the drug molecule can be naturally viewed as language to some extent. In this paper, we investigate how to develop the pretrained model BERT to extract useful molecular substructure information for molecular property prediction. We present a novel end-to-end deep learning framework, named Mol-BERT, that combines an effective molecular representation with pretrained BERT model tailored for molecular property prediction. Specifically, a large-scale prediction BERT model is pretrained to generate the embedding of molecular substructures, by using four million unlabeled drug SMILES (i.e., ZINC 15 and ChEMBL 27). Then, the pretrained BERT model can be fine-tuned on various molecular property prediction tasks. To examine the performance of our proposed Mol-BERT, we conduct several experiments on 4 widely used molecular datasets. In comparison to the traditional and state-of-the-art baselines, the results illustrate that our proposed Mol-BERT can outperform the current sequence-based methods and achieve at least 2% improvement on ROC-AUC score on Tox21, SIDER, and ClinTox dataset.

scholarly journals A Developed Siamese CNN with 3D Adaptive Spatial-Spectral Pyramid Pooling for Hyperspectral Image Classification

2020 ◽  
Vol 12 (12) ◽  
pp. 1964 ◽  
Author(s):  
Mengbin Rao ◽  
Ping Tang ◽  
Zheng Zhang
Keyword(s):  
Transfer Learning ◽  
Hyperspectral Image ◽  
Three Dimensional ◽  
Classification Performance ◽  
Generalization Capability ◽  
Training Strategy ◽  
Learning Framework ◽  
Spectral Bands ◽  
Learning Tasks ◽  
3D Information

Since hyperspectral images (HSI) captured by different sensors often contain different number of bands, but most of the convolutional neural networks (CNN) require a fixed-size input, the generalization capability of deep CNNs to use heterogeneous input to achieve better classification performance has become a research focus. For classification tasks with limited labeled samples, the training strategy of feeding CNNs with sample-pairs instead of single sample has proven to be an efficient approach. Following this strategy, we propose a Siamese CNN with three-dimensional (3D) adaptive spatial-spectral pyramid pooling (ASSP) layer, called ASSP-SCNN, that takes as input 3D sample-pair with varying size and can easily be transferred to another HSI dataset regardless of the number of spectral bands. The 3D ASSP layer can also extract different levels of 3D information to improve the classification performance of the equipped CNN. To evaluate the classification and generalization performance of ASSP-SCNN, our experiments consist of two parts: the experiments of ASSP-SCNN without pre-training and the experiments of ASSP-SCNN-based transfer learning framework. Experimental results on three HSI datasets demonstrate that both ASSP-SCNN without pre-training and transfer learning based on ASSP-SCNN achieve higher classification accuracies than several state-of-the-art CNN-based methods. Moreover, we also compare the performance of ASSP-SCNN on different transfer learning tasks, which further verifies that ASSP-SCNN has a strong generalization capability.

scholarly journals CovNet: A Transfer Learning Framework for Automatic COVID-19 Detection From Crowd-Sourced Cough Sounds

2022 ◽  
Vol 3 ◽  
Author(s):  
Yi Chang ◽  
Xin Jing ◽  
Zhao Ren ◽  
Björn W. Schuller
Keyword(s):  
Transfer Learning ◽  
Large Scale ◽  
Low Cost ◽  
Characteristic Curve ◽  
Training Data ◽  
Small Scale ◽  
Respiratory Sounds ◽  
Learning Framework ◽  
Robust Model ◽  
Cough Sound

Since the COronaVIrus Disease 2019 (COVID-19) outbreak, developing a digital diagnostic tool to detect COVID-19 from respiratory sounds with computer audition has become an essential topic due to its advantages of being swift, low-cost, and eco-friendly. However, prior studies mainly focused on small-scale COVID-19 datasets. To build a robust model, the large-scale multi-sound FluSense dataset is utilised to help detect COVID-19 from cough sounds in this study. Due to the gap between FluSense and the COVID-19-related datasets consisting of cough only, the transfer learning framework (namely CovNet) is proposed and applied rather than simply augmenting the training data with FluSense. The CovNet contains (i) a parameter transferring strategy and (ii) an embedding incorporation strategy. Specifically, to validate the CovNet's effectiveness, it is used to transfer knowledge from FluSense to COUGHVID, a large-scale cough sound database of COVID-19 negative and COVID-19 positive individuals. The trained model on FluSense and COUGHVID is further applied under the CovNet to another two small-scale cough datasets for COVID-19 detection, the COVID-19 cough sub-challenge (CCS) database in the INTERSPEECH Computational Paralinguistics challengE (ComParE) challenge and the DiCOVA Track-1 database. By training four simple convolutional neural networks (CNNs) in the transfer learning framework, our approach achieves an absolute improvement of 3.57% over the baseline of DiCOVA Track-1 validation of the area under the receiver operating characteristic curve (ROC AUC) and an absolute improvement of 1.73% over the baseline of ComParE CCS test unweighted average recall (UAR).

Application of Optimization and Machine Learning for Sentiment Analysis

2021 ◽  
pp. 1-7
Author(s):  
Manitosh Chourasiya ◽  
Prof. Devendra Singh Rathod
Keyword(s):  
Machine Learning ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Learning Algorithm ◽  
Sentiment Classification ◽  
Machine Learning Techniques ◽  
Assessment Scores ◽  
Opinion Extraction ◽  
Learning Techniques ◽  
High Level

Sentiment analysis is called detecting emotions extracted from text features and is known as one of the most important parts of opinion extraction. Through this process, we can determine if a script is positive, negative or neutral. In this research, sentiment analysis is performed with textual data. A text feeling analyzer combines natural language processing (NLP) and machine learning techniques to assign weighted assessment scores to entities, subjects, subjects, and categories within a sentence or phrase. In expressing mood, the polarity of text reviews could be graded on a negative to positive scale using a learning algorithm. The current decade has seen significant developments in artificial intelligence, and the machine learning revolution has changed the entire AI industry. After all, machine learning techniques have become an integral part of any model in today's computing world. However, the ensemble to learning techniques is promise a high level of automation with the extraction of generalized rules for text and sentiment classification activities. This thesis aims to design and implement an optimized functionality matrix using to the ensemble learning for the sentiment classification and its applications.

scholarly journals A Novel Hyperspectral Endmember Extraction Algorithm Based on Online Robust Dictionary Learning

2019 ◽  
Vol 11 (15) ◽  
pp. 1792 ◽  
Author(s):  
Xiaorui Song ◽  
Lingda Wu
Keyword(s):  
Dictionary Learning ◽  
Large Scale ◽  
Hyperspectral Image ◽  
Signal To Noise Ratio ◽  
Extraction Methods ◽  
Computational Time ◽  
Endmember Extraction ◽  
Learning Framework ◽  
Extraction Algorithm ◽  
High Level

Due to the sparsity of hyperspectral images, the dictionary learning framework has been applied in hyperspectral endmember extraction. However, current endmember extraction methods based on dictionary learning are not robust enough in noisy environments. To solve this problem, this paper proposes a novel endmember extraction approach based on online robust dictionary learning, termed EEORDL. Because of the large scale of the hyperspectral image (HSI) data, an online scheme is introduced to reduce the computational time of dictionary learning. In the proposed algorithm, a new form of the objective function is introduced into the dictionary learning process to improve the robustness for noisy HSI data. The experimental results, conducted with both synthetic and real-world hyperspectral datasets, illustrate that the proposed EEORDL outperforms the state-of-the-art approaches under different signal-to-noise ratio (SNR) conditions, especially for high-level noise.

scholarly journals On Reinforcement Learning for Full-Length Game of StarCraft

2019 ◽  
Vol 33 ◽  
pp. 4691-4698 ◽  
Author(s):  
Zhen-Jia Pang ◽  
Ruo-Ze Liu ◽  
Zhou-Yu Meng ◽  
Yi Zhang ◽  
Yang Yu ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Transfer Learning ◽  
Large Scale ◽  
Learning Algorithm ◽  
Full Length ◽  
Action Space ◽  
Hierarchical Architecture ◽  
Difficulty Level ◽  
Future Research ◽  
Grand Challenge

StarCraft II poses a grand challenge for reinforcement learning. The main difficulties include huge state space, varying action space, long horizon, etc. In this paper, we investigate a set of techniques of reinforcement learning for the full-length game of StarCraft II. We investigate a hierarchical approach, where the hierarchy involves two levels of abstraction. One is the macro-actions extracted from expert’s demonstration trajectories, which can reduce the action space in an order of magnitude yet remain effective. The other is a two-layer hierarchical architecture, which is modular and easy to scale. We also investigate a curriculum transfer learning approach that trains the agent from the simplest opponent to harder ones. On a 64×64 map and using restrictive units, we train the agent on a single machine with 4 GPUs and 48 CPU threads. We achieve a winning rate of more than 99% against the difficulty level-1 built-in AI. Through the curriculum transfer learning algorithm and a mixture of combat model, we can achieve over 93% winning rate against the most difficult noncheating built-in AI (level-7) within days. We hope this study could shed some light on the future research of large-scale reinforcement learning.

scholarly journals Estimating nitrogen and phosphorus concentrations in streams and rivers across the contiguous United States: a machine learning framework

2019 ◽  
Author(s):  
Longzhu Shen ◽  
Giuseppe Amatulli ◽  
Tushar Sethi ◽  
Peter Raymond ◽  
Sami Domisch
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Learning Algorithm ◽  
External Validation ◽  
Anthropogenic Activity ◽  
Spatial And Temporal Variability ◽  
Nitrogen And Phosphorus ◽  
Learning Framework ◽  
Environmental Models ◽  
Improved Accuracy

Nitrogen (N) and Phosphorus (P) are essential nutrients for life processes in water bodies but in excessive quantities, they are a significant source of aquatic pollution. Eutrophication has now become widespread due to such an imbalance, and is largely attributed to anthropogenic activity. In view of this phenomenon, we present a new dataset and statistical method for estimating and mapping elemental and compound con- centrations of N and P at a resolution of 30 arc-seconds (∼1 km) for the conterminous US. The model is based on a Random Forest (RF) machine learning algorithm that was fitted with environmental variables and seasonal N and P concentration observations from 230,000 stations spanning across US stream networks. Accounting for spatial and temporal variability offers improved accuracy in the analysis of N and P cycles. The algorithm has been validated with an internal and external validation procedure that is able to explain 70-83% of the variance in the model. The dataset is ready for use as input in a variety of environmental models and analyses, and the methodological framework can be applied to large-scale studies on N and P pollution, which include water quality, species distribution and water ecology research worldwide.

scholarly journals Contactless System with Mask and Temperature Detection

2021 ◽  
pp. 10-18
Author(s):  
Prof. Sheetal Mahadik ◽  
Namrata J. Ravat ◽  
Kunal Y. Singh ◽  
Suvita K. Yadav
Keyword(s):  
Large Scale ◽  
Face Mask ◽  
Temperature Sensing ◽  
Feature Maps ◽  
Temperature Detection ◽  
Learning Techniques ◽  
Multiple Feature ◽  
Public Areas ◽  
Contactless System ◽  
High Level

Coronavirus disease in 2019 has affected the world very badly on a large scale. One of the important protection methods is to wear masks in public areas. Also, while using public services it is important to wear a mask correctly if you want to use their services. However, there is very few researches on face mask detection based on image analysis. In this paper, we propose Face Mask, which is a high-accuracy and efficient face mask detector. The proposed system is a one-stage detector, which consists of a pyramid network to fuse high-level semantic information with multiple feature maps, and a module to focus on detecting face masks. In addition, we also propose a novel cross-class object removal algorithm that will reject predictions with low confidences and the high intersection of the union. Besides, we also focus on the possibilities of implementing Face Mask with a light-weighted neural network MobileNet for embedded or mobile devices. In this paper, we introduce an affordable solution aiming to increase COVID-19 indoor safety, covering relevant aspects: 1) contactless temperature sensing 2) mask detection. Contactless temperature sensing subsystem relies on Arduino Uno using an infrared sensor or thermal camera, while mask detection is performed by leveraging computer vision techniques and Deep Learning Techniques.

scholarly journals Large-Scale Local Online Similarity/Distance Learning Framework Based on Passive/Aggressive

2021 ◽  
Author(s):  
Baida Hamdan ◽  
Davood Zabihzadeh
Keyword(s):  
Distance Learning ◽  
Input Data ◽  
Large Scale ◽  
Learning Algorithm ◽  
Metric Learning ◽  
Distance Measures ◽  
Discrimination Power ◽  
Input Space ◽  
Learning Framework ◽  
Similarity Distance

Similarity/distance measures play a key role in many machine learning, pattern recognition, and data mining algorithms, which leads to the emergence of the metric learning field. Many metric learning algorithms learn a global distance function from data that satisfies the constraints of the problem. However, in many real-world datasets, where the discrimination power of features varies in the different regions of input space, a global metric is often unable to capture the complexity of the task. To address this challenge, local metric learning methods are proposed which learn multiple metrics across the different regions of the input space. Some advantages of these methods include high flexibility and learning a nonlinear mapping, but they typically achieve at the expense of higher time requirements and overfitting problems. To overcome these challenges, this research presents an online multiple metric learning framework. Each metric in the proposed framework is composed of a global and a local component learned simultaneously. Adding a global component to a local metric efficiently reduces the problem of overfitting. The proposed framework is also scalable with both sample size and the dimension of input data. To the best of our knowledge, this is the first local online similarity/distance learning framework based on Passive/Aggressive (PA). In addition, for scalability with the dimension of input data, Dual Random Projection (DRP) is extended for local online learning in the present work. It enables our methods to run efficiently on high-dimensional datasets while maintaining their predictive performance. The proposed framework provides a straightforward local extension to any global online similarity/distance learning algorithm based on PA. Experimental results on some challenging datasets from machine vision community confirm that the extended methods considerably enhance the performance of the related global ones without increasing the time complexity.

scholarly journals Unregistered Biological Words Recognition by Q-Learning with Transfer Learning

2014 ◽  
Vol 2014 ◽  
pp. 1-9
Author(s):  
Fei Zhu ◽  
Quan Liu ◽  
Hui Wang ◽  
Xiaoke Zhou ◽  
Yuchen Fu
Keyword(s):  
Transfer Learning ◽  
Learning Algorithm ◽  
Optimal Solution ◽  
Recall Rate ◽  
Learning Approach ◽  
Target Task ◽  
Q Learning ◽  
Learning Framework ◽  
Speed Up ◽  
Improved Performance

Unregistered biological words recognition is the process of identification of terms that is out of vocabulary. Although many approaches have been developed, the performance approaches are not satisfactory. As the identification process can be viewed as a Markov process, we put forward a Q-learning with transfer learning algorithm to detect unregistered biological words from texts. With the Q-learning, the recognizer can attain the optimal solution of identification during the interaction with the texts and contexts. During the processing, a transfer learning approach is utilized to fully take advantage of the knowledge gained in a source task to speed up learning in a different but related target task. A mapping, required by many transfer learning, which relates features from the source task to the target task, is carried on automatically under the reinforcement learning framework. We examined the performance of three approaches with GENIA corpus and JNLPBA04 data. The proposed approach improved performance in both experiments. The precision, recall rate, andFscore results of our approach surpassed those of conventional unregistered word recognizer as well as those of Q-learning approach without transfer learning.

Sign in / Sign up

Export Citation Format

Share Document