Pub Date : 2020-12-01DOI: 10.1142/S1793351X20300022
Eren Kurshan, Hongda Shen
The rise of digital payments has caused consequential changes in the financial crime landscape. As a result, traditional fraud detection approaches such as rule-based systems have largely become ineffective. Artificial intelligence (AI) and machine learning solutions using graph computing principles have gained significant interest in recent years. Graph-based techniques provide unique solution opportunities for financial crime detection. However, implementing such solutions at industrial-scale in real-time financial transaction processing systems has brought numerous application challenges to light. In this paper, we discuss the implementation difficulties current and next-generation graph solutions face. Furthermore, financial crime and digital payments trends indicate emerging challenges in the continued effectiveness of the detection techniques. We analyze the threat landscape and argue that it provides key insights for developing graph-based solutions.
{"title":"Graph Computing for Financial Crime and Fraud Detection: Trends, Challenges and Outlook","authors":"Eren Kurshan, Hongda Shen","doi":"10.1142/S1793351X20300022","DOIUrl":"https://doi.org/10.1142/S1793351X20300022","url":null,"abstract":"The rise of digital payments has caused consequential changes in the financial crime landscape. As a result, traditional fraud detection approaches such as rule-based systems have largely become ineffective. Artificial intelligence (AI) and machine learning solutions using graph computing principles have gained significant interest in recent years. Graph-based techniques provide unique solution opportunities for financial crime detection. However, implementing such solutions at industrial-scale in real-time financial transaction processing systems has brought numerous application challenges to light. In this paper, we discuss the implementation difficulties current and next-generation graph solutions face. Furthermore, financial crime and digital payments trends indicate emerging challenges in the continued effectiveness of the detection techniques. We analyze the threat landscape and argue that it provides key insights for developing graph-based solutions.","PeriodicalId":217956,"journal":{"name":"Int. J. Semantic Comput.","volume":"98 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133553737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1142/S1793351X20500063
Eren Kurshan, H. Li, Mingoo Seok, Yuan Xie
Over the last decade, artificial intelligence has found many applications areas in the society. As AI solutions have become more sophistication and the use cases grew, they highlighted the need to address performance and energy efficiency challenges faced during the implementation process. To address these challenges, there has been growing interest in neuromorphic chips. Neuromorphic computing relies on non von Neumann architectures as well as novel devices, circuits and manufacturing technologies to mimic the human brain. Among such technologies, 3D integration is an important enabler for AI hardware and the continuation of the scaling laws. In this paper, we overview the unique opportunities 3D integration provides in neuromorphic chip design, discuss the emerging opportunities in next generation neuromorphic architectures and review the obstacles. Neuromorphic architectures, which relied on the brain for inspiration and emulation purposes, face grand challenges due to the limited understanding of the functionality and the architecture of the human brain. Yet, high-levels of investments are dedicated to develop neuromorphic chips. We argue that 3D integration not only provides strategic advantages to the cost-effective and flexible design of neuromorphic chips, it may provide design flexibility in incorporating advanced capabilities to further benefits the designs in the future.
{"title":"A Case for 3D Integrated System Design for Neuromorphic Computing & AI Applications","authors":"Eren Kurshan, H. Li, Mingoo Seok, Yuan Xie","doi":"10.1142/S1793351X20500063","DOIUrl":"https://doi.org/10.1142/S1793351X20500063","url":null,"abstract":"Over the last decade, artificial intelligence has found many applications areas in the society. As AI solutions have become more sophistication and the use cases grew, they highlighted the need to address performance and energy efficiency challenges faced during the implementation process. To address these challenges, there has been growing interest in neuromorphic chips. Neuromorphic computing relies on non von Neumann architectures as well as novel devices, circuits and manufacturing technologies to mimic the human brain. Among such technologies, 3D integration is an important enabler for AI hardware and the continuation of the scaling laws. In this paper, we overview the unique opportunities 3D integration provides in neuromorphic chip design, discuss the emerging opportunities in next generation neuromorphic architectures and review the obstacles. Neuromorphic architectures, which relied on the brain for inspiration and emulation purposes, face grand challenges due to the limited understanding of the functionality and the architecture of the human brain. Yet, high-levels of investments are dedicated to develop neuromorphic chips. We argue that 3D integration not only provides strategic advantages to the cost-effective and flexible design of neuromorphic chips, it may provide design flexibility in incorporating advanced capabilities to further benefits the designs in the future.","PeriodicalId":217956,"journal":{"name":"Int. J. Semantic Comput.","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125118913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1142/S1793351X20300010
Alexandros Britzolakis, H. Kondylakis, N. Papadakis
Sentiment analysis over social media platforms has been an active case of study for more than a decade. This occurs due to the constant rising of Internet users over these platforms, as well as to the increasing interest of companies for monitoring the opinion of customers over commercial products. Most of these platforms provide free, online services such as the creation of interactive web communities, multimedia content uploading, etc. This new way of communication has affected human societies as it shaped the way by which an opinion can be expressed, sparking the era of digital revolution. One of the most profound examples of social networking platforms for opinion mining is Twitter as it is a great source for extracting news and a platform which politicians tend to use frequently. In addition to that, the character limitation per posted tweet (maximum of 280 characters) makes it easier for automated tools to extract its underlying sentiment. In this review paper, we present a variety of lexicon-based tools as well as machine learning algorithms used for sentiment extraction. Furthermore, we present additional implementations used for political sentiment analysis over Twitter as well as additional open topics. We hope the review will help readers to understand this scientifically rich area, identify best options for their work and work on open topics.
{"title":"A Review on Lexicon-Based and Machine Learning Political Sentiment Analysis Using Tweets","authors":"Alexandros Britzolakis, H. Kondylakis, N. Papadakis","doi":"10.1142/S1793351X20300010","DOIUrl":"https://doi.org/10.1142/S1793351X20300010","url":null,"abstract":"Sentiment analysis over social media platforms has been an active case of study for more than a decade. This occurs due to the constant rising of Internet users over these platforms, as well as to the increasing interest of companies for monitoring the opinion of customers over commercial products. Most of these platforms provide free, online services such as the creation of interactive web communities, multimedia content uploading, etc. This new way of communication has affected human societies as it shaped the way by which an opinion can be expressed, sparking the era of digital revolution. One of the most profound examples of social networking platforms for opinion mining is Twitter as it is a great source for extracting news and a platform which politicians tend to use frequently. In addition to that, the character limitation per posted tweet (maximum of 280 characters) makes it easier for automated tools to extract its underlying sentiment. In this review paper, we present a variety of lexicon-based tools as well as machine learning algorithms used for sentiment extraction. Furthermore, we present additional implementations used for political sentiment analysis over Twitter as well as additional open topics. We hope the review will help readers to understand this scientifically rich area, identify best options for their work and work on open topics.","PeriodicalId":217956,"journal":{"name":"Int. J. Semantic Comput.","volume":"87 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120882124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1142/S1793351X20500087
Joseph R. Barr, Peter Shaw, F. Abu-Khzam, Tyler Thatcher, Sheng Yu
We present an empirical analysis of the source code of the Fluoride Bluetooth module, which is a part of standard Android OS distribution, by exhibiting a novel approach for classifying and scoring source code and vulnerability rating. Our workflow combines deep learning, combinatorial optimization, heuristics and machine learning. A combination of heuristics and deep learning is used to embed function (and method) labels into a low-dimensional Euclidean space. Because the corpus of the Fluoride source code is rather limited (containing approximately 12,000 functions), a straightforward embedding (using, e.g. code2vec) is untenable. To overcome the challenge of dearth of data, it is necessary to go through an intermediate step of Byte-Pair Encoding. Subsequently, we embed the tokens from which we assemble an embedding of function/method labels. Long short-term memory network (LSTM) is used to embed tokens. The next step is to form a distance matrix consisting of the cosines between every pairs of vectors (function embedding) which in turn is interpreted as a (combinatorial) graph whose vertices represent functions, and edges correspond to entries whose value exceed some given threshold. Cluster-Editing is then applied to partition the vertex set of the graph into subsets representing “dense graphs,” that are nearly complete subgraphs. Finally, the vectors representing the components, plus additional heuristic-based features are used as features to model the components for vulnerability risk.
{"title":"Vulnerability Rating of Source Code with Token Embedding and Combinatorial Algorithms","authors":"Joseph R. Barr, Peter Shaw, F. Abu-Khzam, Tyler Thatcher, Sheng Yu","doi":"10.1142/S1793351X20500087","DOIUrl":"https://doi.org/10.1142/S1793351X20500087","url":null,"abstract":"We present an empirical analysis of the source code of the Fluoride Bluetooth module, which is a part of standard Android OS distribution, by exhibiting a novel approach for classifying and scoring source code and vulnerability rating. Our workflow combines deep learning, combinatorial optimization, heuristics and machine learning. A combination of heuristics and deep learning is used to embed function (and method) labels into a low-dimensional Euclidean space. Because the corpus of the Fluoride source code is rather limited (containing approximately 12,000 functions), a straightforward embedding (using, e.g. code2vec) is untenable. To overcome the challenge of dearth of data, it is necessary to go through an intermediate step of Byte-Pair Encoding. Subsequently, we embed the tokens from which we assemble an embedding of function/method labels. Long short-term memory network (LSTM) is used to embed tokens. The next step is to form a distance matrix consisting of the cosines between every pairs of vectors (function embedding) which in turn is interpreted as a (combinatorial) graph whose vertices represent functions, and edges correspond to entries whose value exceed some given threshold. Cluster-Editing is then applied to partition the vertex set of the graph into subsets representing “dense graphs,” that are nearly complete subgraphs. Finally, the vectors representing the components, plus additional heuristic-based features are used as features to model the components for vulnerability risk.","PeriodicalId":217956,"journal":{"name":"Int. J. Semantic Comput.","volume":"67 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124464191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1142/s1793351x20400152
Vishnunarayan Girishan Prabhu, L. Stanley, Robert Morgan
Pain and anxiety are common accompaniments of surgery, and opioids have been the mainstay of pain management for decades, with about 80% of the surgical population leaving the hospital with an opioid prescription. Moreover, patients receiving an opioid prescription after short-stay surgeries have a 44% increased risk of long-term opioid use, and about one in 16 surgical patients becomes a long-term user. Current opioid abuse and addiction now place the US in an “opioid epidemic,” and calls for alternative pain management mechanisms. To mitigate the preoperative anxiety and postoperative pain, we developed a virtual reality (VR) experience based on Attention Restoration Theory (ART) and integrated the user’s heart rate variability (HRV) biofeedback to create an adaptive environment. A randomized control trial among 16 Total Knee Arthroplasty (TKA) patients undergoing surgery at Patewood Memorial Hospital, Greenville, SC demonstrated that patients experiencing the adaptive VR environment reported a significant decrease in preoperative anxiety ([Formula: see text]) and postoperative pain ([Formula: see text]) after the VR intervention. These results were also supported by the physiological measures where there was a significant increase in RR Interval (RRI) ([Formula: see text]) and a significant decrease in the low frequency (LF)/high frequency (HF) ratio ([Formula: see text]) and respiration rate (RR) ([Formula: see text]).
{"title":"A Biofeedback Enhanced Adaptive Virtual Reality Environment for Managing Surgical Pain and Anxiety","authors":"Vishnunarayan Girishan Prabhu, L. Stanley, Robert Morgan","doi":"10.1142/s1793351x20400152","DOIUrl":"https://doi.org/10.1142/s1793351x20400152","url":null,"abstract":"Pain and anxiety are common accompaniments of surgery, and opioids have been the mainstay of pain management for decades, with about 80% of the surgical population leaving the hospital with an opioid prescription. Moreover, patients receiving an opioid prescription after short-stay surgeries have a 44% increased risk of long-term opioid use, and about one in 16 surgical patients becomes a long-term user. Current opioid abuse and addiction now place the US in an “opioid epidemic,” and calls for alternative pain management mechanisms. To mitigate the preoperative anxiety and postoperative pain, we developed a virtual reality (VR) experience based on Attention Restoration Theory (ART) and integrated the user’s heart rate variability (HRV) biofeedback to create an adaptive environment. A randomized control trial among 16 Total Knee Arthroplasty (TKA) patients undergoing surgery at Patewood Memorial Hospital, Greenville, SC demonstrated that patients experiencing the adaptive VR environment reported a significant decrease in preoperative anxiety ([Formula: see text]) and postoperative pain ([Formula: see text]) after the VR intervention. These results were also supported by the physiological measures where there was a significant increase in RR Interval (RRI) ([Formula: see text]) and a significant decrease in the low frequency (LF)/high frequency (HF) ratio ([Formula: see text]) and respiration rate (RR) ([Formula: see text]).","PeriodicalId":217956,"journal":{"name":"Int. J. Semantic Comput.","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131772801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1142/s1793351x2050004x
Maria Krommyda, Verena Kantere
As more and more datasets become available, their utilization in different applications increases in popularity. Their volume and production rate, however, means that their quality and content control is in most cases non-existing, resulting in many datasets that contain inaccurate information of low quality. Especially, in the field of conversational assistants, where the datasets come from many heterogeneous sources with no quality assurance, the problem is aggravated. We present here an integrated platform that creates task- and topic-specific conversational datasets to be used for training conversational agents. The platform explores available conversational datasets, extracts information based on semantic similarity and relatedness, and applies a weight-based score function to rank the information based on its value for the specific task and topic. The finalized dataset can then be used for the training of an automated conversational assistance over accurate data of high quality.
{"title":"Semantic Analysis for Conversational Datasets: Improving Their Quality Using Semantic Relationships","authors":"Maria Krommyda, Verena Kantere","doi":"10.1142/s1793351x2050004x","DOIUrl":"https://doi.org/10.1142/s1793351x2050004x","url":null,"abstract":"As more and more datasets become available, their utilization in different applications increases in popularity. Their volume and production rate, however, means that their quality and content control is in most cases non-existing, resulting in many datasets that contain inaccurate information of low quality. Especially, in the field of conversational assistants, where the datasets come from many heterogeneous sources with no quality assurance, the problem is aggravated. We present here an integrated platform that creates task- and topic-specific conversational datasets to be used for training conversational agents. The platform explores available conversational datasets, extracts information based on semantic similarity and relatedness, and applies a weight-based score function to rank the information based on its value for the specific task and topic. The finalized dataset can then be used for the training of an automated conversational assistance over accurate data of high quality.","PeriodicalId":217956,"journal":{"name":"Int. J. Semantic Comput.","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121062559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1142/s1793351x20400127
Arno Hartholt, Edward Fast, Adam Reilly, W. Whitcup, Matt Liewer, S. Mozgai
We present an extension of the Virtual Human Toolkit to include a range of computing platforms, including mobile, web, Virtual Reality (VR) and Augmented Reality (AR). The Toolkit uses a mix of in-house and commodity technologies to support audio-visual sensing, speech recognition, natural language processing, nonverbal behavior generation and realization, text-to-speech generation and rendering. It has been extended to support computing platforms beyond Windows by leveraging microservices. The resulting framework maintains the modularity of the underlying architecture, allows re-use of both logic and content through cloud services, and is extensible by porting lightweight clients. We present the current state of the framework, discuss how we model and animate our characters, and offer lessons learned through several use cases, including expressive character animation in seated VR, shared space and navigation in room-scale VR, autonomous AI in mobile AR, and real-time user performance feedback leveraging mobile sensors in headset AR.
{"title":"Multi-Platform Expansion of the Virtual Human Toolkit: Ubiquitous Conversational Agents","authors":"Arno Hartholt, Edward Fast, Adam Reilly, W. Whitcup, Matt Liewer, S. Mozgai","doi":"10.1142/s1793351x20400127","DOIUrl":"https://doi.org/10.1142/s1793351x20400127","url":null,"abstract":"We present an extension of the Virtual Human Toolkit to include a range of computing platforms, including mobile, web, Virtual Reality (VR) and Augmented Reality (AR). The Toolkit uses a mix of in-house and commodity technologies to support audio-visual sensing, speech recognition, natural language processing, nonverbal behavior generation and realization, text-to-speech generation and rendering. It has been extended to support computing platforms beyond Windows by leveraging microservices. The resulting framework maintains the modularity of the underlying architecture, allows re-use of both logic and content through cloud services, and is extensible by porting lightweight clients. We present the current state of the framework, discuss how we model and animate our characters, and offer lessons learned through several use cases, including expressive character animation in seated VR, shared space and navigation in room-scale VR, autonomous AI in mobile AR, and real-time user performance feedback leveraging mobile sensors in headset AR.","PeriodicalId":217956,"journal":{"name":"Int. J. Semantic Comput.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133626965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1142/S1793351X20400139
Alisha Sharma, Ryan Nett, Jonathan Ventura
We introduce a convolutional neural network model for unsupervised learning of depth and ego-motion from cylindrical panoramic video. Panoramic depth estimation is an important technology for applications such as virtual reality, 3D modeling, and autonomous robotic navigation. In contrast to previous approaches for applying convolutional neural networks to panoramic imagery, we use the cylindrical panoramic projection which allows for the use of the traditional CNN layers such as convolutional filters and max pooling without modification. Our evaluation of synthetic and real data shows that unsupervised learning of depth and ego-motion on cylindrical panoramic images can produce high-quality depth maps and that an increased field-of-view improves ego-motion estimation accuracy. We create two new datasets to evaluate our approach: a synthetic dataset created using the CARLA simulator, and Headcam, a novel dataset of panoramic video collected from a helmet-mounted camera while biking in an urban setting. We also apply our network to the problem of converting monocular panoramas to stereo panoramas.
{"title":"Unsupervised Learning of Depth and Ego-Motion from Cylindrical Panoramic Video with Applications for Virtual Reality","authors":"Alisha Sharma, Ryan Nett, Jonathan Ventura","doi":"10.1142/S1793351X20400139","DOIUrl":"https://doi.org/10.1142/S1793351X20400139","url":null,"abstract":"We introduce a convolutional neural network model for unsupervised learning of depth and ego-motion from cylindrical panoramic video. Panoramic depth estimation is an important technology for applications such as virtual reality, 3D modeling, and autonomous robotic navigation. In contrast to previous approaches for applying convolutional neural networks to panoramic imagery, we use the cylindrical panoramic projection which allows for the use of the traditional CNN layers such as convolutional filters and max pooling without modification. Our evaluation of synthetic and real data shows that unsupervised learning of depth and ego-motion on cylindrical panoramic images can produce high-quality depth maps and that an increased field-of-view improves ego-motion estimation accuracy. We create two new datasets to evaluate our approach: a synthetic dataset created using the CARLA simulator, and Headcam, a novel dataset of panoramic video collected from a helmet-mounted camera while biking in an urban setting. We also apply our network to the problem of converting monocular panoramas to stereo panoramas.","PeriodicalId":217956,"journal":{"name":"Int. J. Semantic Comput.","volume":"516 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133132860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1142/s1793351x20400140
James R. Kubricht, A. Santamaría-Pang, Chinmaya Devaraj, Aritra Chowdhury, P. Tu
Recent unsupervised learning approaches have explored the feasibility of semantic analysis and interpretation of imagery using Emergent Language (EL) models. As EL requires some form of numerical embedding as input, it remains unclear which type is required in order for the EL to properly capture key semantic concepts associated with a given domain. In this paper, we compare unsupervised and supervised approaches for generating embeddings across two experiments. In Experiment 1, data are produced using a single-agent simulator. In each episode, a goal-driven agent attempts to accomplish a number of tasks in a synthetic cityscape environment which includes houses, banks, theaters and restaurants. In Experiment 2, a comparatively smaller dataset is produced where one or more objects demonstrate various types of physical motion in a 3D simulator environment. We investigate whether EL models generated from embeddings of raw pixel data produce expressions that capture key latent concepts (i.e. an agent’s motivations or physical motion types) in each environment. Our initial experiments show that the supervised learning approaches yield embeddings and EL descriptions that capture meaningful concepts from raw pixel inputs. Alternatively, embeddings from an unsupervised learning approach result in greater ambiguity with respect to latent concepts.
{"title":"Emergent Languages from Pretrained Embeddings Characterize Latent Concepts in Dynamic Imagery","authors":"James R. Kubricht, A. Santamaría-Pang, Chinmaya Devaraj, Aritra Chowdhury, P. Tu","doi":"10.1142/s1793351x20400140","DOIUrl":"https://doi.org/10.1142/s1793351x20400140","url":null,"abstract":"Recent unsupervised learning approaches have explored the feasibility of semantic analysis and interpretation of imagery using Emergent Language (EL) models. As EL requires some form of numerical embedding as input, it remains unclear which type is required in order for the EL to properly capture key semantic concepts associated with a given domain. In this paper, we compare unsupervised and supervised approaches for generating embeddings across two experiments. In Experiment 1, data are produced using a single-agent simulator. In each episode, a goal-driven agent attempts to accomplish a number of tasks in a synthetic cityscape environment which includes houses, banks, theaters and restaurants. In Experiment 2, a comparatively smaller dataset is produced where one or more objects demonstrate various types of physical motion in a 3D simulator environment. We investigate whether EL models generated from embeddings of raw pixel data produce expressions that capture key latent concepts (i.e. an agent’s motivations or physical motion types) in each environment. Our initial experiments show that the supervised learning approaches yield embeddings and EL descriptions that capture meaningful concepts from raw pixel inputs. Alternatively, embeddings from an unsupervised learning approach result in greater ambiguity with respect to latent concepts.","PeriodicalId":217956,"journal":{"name":"Int. J. Semantic Comput.","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116135363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-09DOI: 10.1142/s1793351x20500038
Dongfang Liu, Yaqin Wang, Tian Chen, E. Matson
Lane detection is a crucial factor for self-driving cars to achieve a fully autonomous mode. Due to its importance, lane detection has drawn wide attention in recent years for autonomous driving. O...
{"title":"Accurate Lane Detection for Self-Driving Cars: An Approach Based on Color Filter Adjustment and K-Means Clustering Filter","authors":"Dongfang Liu, Yaqin Wang, Tian Chen, E. Matson","doi":"10.1142/s1793351x20500038","DOIUrl":"https://doi.org/10.1142/s1793351x20500038","url":null,"abstract":"Lane detection is a crucial factor for self-driving cars to achieve a fully autonomous mode. Due to its importance, lane detection has drawn wide attention in recent years for autonomous driving. O...","PeriodicalId":217956,"journal":{"name":"Int. J. Semantic Comput.","volume":"295 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123239948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：