Abstracts of latest research papers in Artificial Intelligence
Artificial Intelligence
halka açık
[search 0]
Bulabildiğimiz En İyi Artificial Intelligence Podcast'ler
Bulabildiğimiz En İyi Artificial Intelligence Podcast'ler
With the rise of artificial intelligence in use today including applications like Siri, Alexa, Tesla, Cortana, Cogito, Google Now, and even Netflix, podcasts are a great alternative to keep yourself updated. We've gathered a list of podcasts available for you about this technology where you can get the latest news and trends plus learn more about how AI works and its impact on our lives.
T
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)


1
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Sam Charrington
Machine learning and artificial intelligence are dramatically changing the way businesses operate and people live. The TWIML AI Podcast brings the top minds and ideas from the world of ML and AI to a broad and influential community of ML/AI researchers, data scientists, engineers and tech-savvy business and IT leaders. Hosted by Sam Charrington, a sought after industry analyst, speaker, commentator and thought leader. Technologies covered include machine learning, artificial intelligence, de ...
A
AI Today Podcast: Artificial Intelligence Insights, Experts, and Opinion


Real-World, Industry and Adoption focused Market Research and Intelligence on AI.
人
人工智慧醫學組織 Artificial Intelligence Medicine AIM


1
人工智慧醫學組織 Artificial Intelligence Medicine AIM
北醫大人工智慧醫學組織
透過世界各地的學界、業界、醫界、新創產業的前輩經驗分享或未來新知,得到自己學習的目標與生職涯規劃相關建議,以了解人工智慧的浪潮 -- Hosting provided by SoundOn
What is AI? How will it affect your life, your work, and your world?
D
Data Futurology - Leadership And Strategy in Artificial Intelligence, Machine Learning, Data Science


1
Data Futurology - Leadership And Strategy in Artificial Intelligence, Machine Learning, Data Science
Felipe Flores
Artificial intelligence is a tremendously beneficial technology that's advancing at an incredibly rapid pace. As more and more organisations adopt and implement AI we find that the main challenges are not in the technology itself but in the human side, ie: the approaches, chosen problems and what's called 'the last mile', etc. That's why Data Futurology focuses on the leadership side of AI and how to get the most value from it. Join me, Felipe Flores, a Data Science executive with almost 20 ...
AI with AI explores the latest breakthroughs in artificial intelligence and autonomy, and discusses the technological and military implications. Join Andy Ilachinski and David Broyles as they explain the latest developments in this rapidly evolving field. The views expressed here are those of the commentators and do not necessarily reflect the views of CNA or any of its sponsors.
C
Conversations on Applied AI - Stories from Experts in Artificial Intelligence


Welcome to the Conversations on Applied AI Podcast where Justin Grammens and the team at Emerging Technologies North talk with experts in the fields of Artificial Intelligence and Deep Learning. In each episode, we cut through the hype and dive into how these technologies are being applied to real-world problems today. We hope that you find this episode educational and applicable to your industry and connect with us to learn more about our organization at AppliedAI.MN. Enjoy!
I
If What If - Artificial Intelligence & Virtual Reality


1
If What If - Artificial Intelligence & Virtual Reality
If What If (IWI)
Dream It! Imagine It! Create It! "If What If" (IWI) is an educational, consulting, and development company where our expertise is in Artificial Intelligence (AI), Virtual Reality (VR), Virtual Worlds (VW), and the Metaverse. "If What If" are a group of Futurists, computer analysts, data scientists, and researchers who believe that Virtual Reality (VR), Augmented Reality (AR), Extended Reality (XR), and the Metaverse coupled with AI is one of the next great technological frontiers. Our podcas ...
H
HumAIn Podcast - Artificial Intelligence, Data Science, Developer Tools, and Technical Education


1
HumAIn Podcast - Artificial Intelligence, Data Science, Developer Tools, and Technical Education
David Yakobovitch
David Yakobovitch explores AI for consumers through fireside conversations with industry thought leaders on HumAIn. From Chief Data Scientists and AI Advisors, to Leaders who advance AI for All, the HumAIn Podcast is the channel to release new AI products, to learn about industry trends, and to bridge the gap between humans and machines in the Fourth Industrial Revolution.
C
Courageous! Artificial Intelligence & Cybersecurity Think Tank with Dr. Rollan Roberts


1
Courageous! Artificial Intelligence & Cybersecurity Think Tank with Dr. Rollan Roberts
Dr. Rollan Roberts II
Dr. Rollan Roberts is an advisor and resource to national governments on strong Artificial Intelligence and quantum-proof Cybersecurity and was nominated to Central Command's Department of Defense Civilian Task Force. He is the CEO of Courageous!, a superhuman AI and Cybersecurity research and product development think tank that serves advanced national security initiatives of national governments. He served as CEO of the Hoverboard company, creating the best-selling consumer product worldwi ...
A
AI and Us - what Artificial Intelligence means for our lives


1
AI and Us - what Artificial Intelligence means for our lives
Alexander von Humboldt Foundation
Artificial intelligence is already controlling washing machines and translation assistants and helping doctors reach a diagnosis. It is changing our working lives and our leisure time. AI is making our lives easier and, ideally, even better! AI raises expectations, fears and hopes. And it involves risks. It’s all about personal autonomy and freedom, about security as well as sustainability and even global equity. AI between a promising future and a brave new world. Leading AI experts talk ab ...
A
Artificial Intelligence and Product Strategy podcast.


Follow my podcasts to learn how successful companies launch Artificial Intelligence-driven products and implement product strategy. You will find a vast number of robust case studies, insights, and manuals.
Presented by podcast network VoiceFirst.FM, Artificial Intelligence is a monthly show devoted to all things A.I. Hosted by Bradley Metrock, CEO of Score Publishing and host of VoiceFirst.FM shows "This Week In Voice" and "The VoiceFirst Roundtable."
As the world's first B2B AI platform, appliedAI helps organizations explore, plan and implement leading edge AI solutions in 100+ use cases along the enterprise value chain.
R
Roborah - podcast made by Artificial Intelligence


1
Roborah - podcast made by Artificial Intelligence
Ricky Vuckovic
A podcast that's scripted and voiced by artificial intelligence. Yep, no humans in the writing and delivery of this podcast!
A
Artificial Intelligence Podcast with Dr. Tony Hoang

1
Artificial Intelligence Podcast with Dr. Tony Hoang
Dr. Tony Hoang
Anything and everything that has to do with Artificial Intelligence, Machine Learning and Data Science
Get knowledge and inspiration to apply artificial intelligence to drug development. Discover startups applying machine learning to biomedical research. Hear how biotech and pharma companies use AI to speed discovery and cut costs. Learn from academic researchers pushing boundaries in applying computation to biology. We interview leaders transforming drug development with data and algorithms. Subscribe now and never miss an episode!
A
AUTOMATION, RPA, ARTIFICIAL INTELLIGENCE, LEADERSHIP and all its interwinding overlaps...

Danilo McGarry is a prominent leader, coach and Keynote speaker in the topics of Automation (and all its related areas: Artificial Intelligence/RPA/Machine Learning/Neural Networks/Deep Learning/Transformation) - to read more about the creator of this space please visit www.danilomcgarry.com
A
Artificial Intelligence on the Battlefield


1
Artificial Intelligence on the Battlefield
Shephard Media
Artificial intelligence technologies are undoubtedly beginning to change the face of modern warfare. AI and machine learning applications promise to enhance productivity, reduce user workload, and operate more quickly than humans. But, this doesn’t come without its challenges. The Artificial Intelligence on the Battlefield podcast dives into these issues and more, looking at just how will AI reshape the future of warfare? Created by Shephard Studio, the Artificial Intelligence on the Battlef ...
T
Talking Robots - The Podcast on Robotics and Artificial Intelligence


1
Talking Robots - The Podcast on Robotics and Artificial Intelligence
Laboratory of Intelligent Systems
Talking Robots is a podcast featuring interviews with high-profile professionals in Robotics and Artificial Intelligence for an inside view on the science, technology, and business of intelligent robotics. It is managed and sponsored by the Laboratory of Intelligent Systems (LIS) at the EPFL in Lausanne, Switzerland.
Join us on Beyond The Lab as we bring you authentic conversations discussing emerging technology, A.I. Ethics, careers, and resources to take your artificial intelligence journey to the next level.
A
AI LITERACY - A Podcast about Artificial Intelligence


1
AI LITERACY - A Podcast about Artificial Intelligence
AI LITERACY
Dive into the world of Artificial Intelligence with your host Anna-Regina Entus - founder and president of the AI in Management Association and fellow of the AI Research Center at emlyon business school in Paris. Together with guest speakers from around the globe, I am helping you make sense of AI and share insights on the latest innovations in the world of Artificial Intelligence. Episodes 1-6: Hosted by Anna-Regina Entus and Victoria Rugli from Episode 7: Hosted by Anna-Regina Entus
T
The Artificial Intelligence Podcast | BNR


1
The Artificial Intelligence Podcast | BNR
BNR Nieuwsradio
AI in Real Life: machine learning, neural networks, deep learning. We’re on the threshold of something big. Join us as we explore what this means, not just for humanity in the future, but also for you and me, tomorrow.
A
A Word On Artificial Intelligence (A.I.)


1
A Word On Artificial Intelligence (A.I.)
Primedia Broadcasting
An introduction to machine learning to assist business leaders to understand what it can and can't do. In the three episodes, you will get a sense of the potential impact, the nature and types of models available and case studies that may apply to your industry. Allan Kent is the Head of Digital at Primedia Broadcasting and is the host of this series.
A
Applied Artificial Intelligence For Business


TOPBOTS educates business leaders on high-impact applications of modern machine learning and AI techniques and helps leading organizations adopt and implement emerging technologies. We run the largest publication and community for enterprise AI professionals to learn about the latest machine learning and automation solutions and exchange insights with each other. Through education and community, we inspire you to think creatively about how AI can be used to improve lives, revolutionize indus ...
C
Courageous! Artificial Intelligence & Cybersecurity Think Tank with Dr. Rollan Roberts


1
Understanding Monetary Systems and Assets
1:14:30
1:14:30
Daha Sonra Çal
Daha Sonra Çal
Listeler
Beğen
Beğenildi
1:14:30
Dr. Rollan Roberts II tarafından oluşturuldu
C
Conversations on Applied AI - Stories from Experts in Artificial Intelligence


1
Building Thinking Machines with Knowledge
53:03
53:03
Daha Sonra Çal
Daha Sonra Çal
Listeler
Beğen
Beğenildi
53:03
The conversation this week is with Bryant Cruse. Bryant has been a pioneer in the application of AI technology to difficult real-world problems. He graduated from St. John's College in Annapolis, Maryland, where he acquired his lifelong interest in the philosophy of Epistemology. Or how we know what we know. After serving for eight years as a naval…
A
Artificial Intelligence: Paper Time

Sumith Kulal, Jiayuan Mao, Alex Aiken, Jiajun WuAbstractWe introduce Programmatic Motion Concepts, a hierarchical motion representation for human actions that captures both low-level motion and high-level description as motion concepts. This representation enables human motion description, interactive editing, and controlled synthesis of novel vide…
A
Artificial Intelligence and You

1
106 - Guest: Ben Goertzel, AGI researcher, SingularityNET Founder
30:00
30:00
Daha Sonra Çal
Daha Sonra Çal
Listeler
Beğen
Beğenildi
30:00
This and all episodes at: https://aiandyou.net/ . We've talked a lot about artificial general intelligence (AGI) on the show, but never as much as in this interview, when we talk with Mr. AGI himself, Ben Goertzel. Ben wrote a book, Artificial General Intelligence, founded the AGI Society and SingularityNET, and wrote Ten Years to the Singularity i…
T
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)


1
More Language, Less Labeling with Kate Saenko - #580
47:01
47:01
Daha Sonra Çal
Daha Sonra Çal
Listeler
Beğen
Beğenildi
47:01
Today we continue our CVPR series joined by Kate Saenko, an associate professor at Boston University and a consulting professor for the MIT-IBM Watson AI Lab. In our conversation with Kate, we explore her research in multimodal learning, which she spoke about at the Multimodal Learning and Applications Workshop, one of a whopping 6 workshops she sp…
I
If What If - Artificial Intelligence & Virtual Reality


1
The 9 Pillars Of The Metaverse Series - Part Two: Immersion
32:40
32:40
Daha Sonra Çal
Daha Sonra Çal
Listeler
Beğen
Beğenildi
32:40
The 9 Pillars Of The Metaverse Series - Part Two: Immersion The Definitive Series on Understanding the Metaverse & Virtual Worlds There is so much confusion about Virtual Reality and the Metaverse. At If-What-If, (IWI), we are producing an educational video and podcast series, on the Metaverse and Virtual Worlds. "The 9 Pillars Of The Metaverse" se…
D
Data Futurology - Leadership And Strategy in Artificial Intelligence, Machine Learning, Data Science


1
#194 Establishing Best-in-Class Multi-Cloud Strategy with Kieran Clulow, Director of Data Platforms at IAG and Stijn De Lathouwers, Head of Data Platforms and Engineering at Suncorp
37:03
37:03
Daha Sonra Çal
Daha Sonra Çal
Listeler
Beğen
Beğenildi
37:03
This special episode is a recording from a live webinar we ran back in February as part of our Future proofing your data platforms online event covering how to establish a best in class multi-cloud strategy. Felipe explored all aspects of a multi-cloud strategy, including simplifying your data architecture, regardless of whether your systems are ru…
A
AI with AI: Artificial Intelligence with Andy Ilachinski


1
RAI, consumers’ co-operative
44:23
44:23
Daha Sonra Çal
Daha Sonra Çal
Listeler
Beğen
Beğenildi
44:23
CNA colleagues Kaia Haney and Heather Roff join Andy and Dave to discuss Responsible AI. They discuss the recent Inclusive National Security seminar on AI and National Security: Gender, Race, and Algorithms. The keynote speaker, Elizabeth Adams spoke on the challenges that society faces in integrating AI technologies in an inclusive fashion, and sh…
A
AI Today Podcast: Artificial Intelligence Insights, Experts, and Opinion


1
AI Today Podcast: AI in the Cloud
40:04
40:04
Daha Sonra Çal
Daha Sonra Çal
Listeler
Beğen
Beğenildi
40:04
In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer discuss what AI in the cloud really means. They break down what is the cloud with a technical definition and then an economic definition to level set the topic and then dig into the question: What does AI have to do with the Cloud? Continue reading AI Today Podcast: AI i…
H
HumAIn Podcast - Artificial Intelligence, Data Science, Developer Tools, and Technical Education


1
Steven Shwartz: How AI Will Impact Society Over the Next Ten Years
34:14
34:14
Daha Sonra Çal
Daha Sonra Çal
Listeler
Beğen
Beğenildi
34:14
[Audio] Podcast: Play in new window | Download Subscribe: Google Podcasts | Spotify | Stitcher | TuneIn | RSS Steve received his PhD from Johns Hopkins University in Cognitive Science where he began his AI research and also taught Statistics at Towson State University. After receiving his PhD in 1979, AI pioneer Roger Schank invited Steve to join t…
A
Artificial Intelligence: Paper Time

Jean-Stanislas Denain, Jacob SteinhardtAbstractTransparency methods such as model visualizations provide information that outputs alone might miss, since they describe the internals of neural networks. But can we trust that model explanations reflect model behavior? For instance, can they diagnose abnormal behavior such as backdoors or shape bias? …
A
Artificial Intelligence: Paper Time

Kenji Kawaguchi, Zhun Deng, Kyle Luh, Jiaoyang HuangAbstractThis paper proves that robustness implies generalization via data-dependent generalization bounds. As a result, robustness and generalization are shown to be connected closely in a data-dependent manner. Our bounds improve previous bounds in two directions, to solve an open problem that ha…
A
Artificial Intelligence: Paper Time

Alexander Matt Turner, Prasad TadepalliAbstractIf capable AI agents are generally incentivized to seek power in service of the objectives we specify for them, then these systems will pose enormous risks, in addition to enormous benefits. In fully observable environments, most reward functions have an optimal policy which seeks power by keeping opti…
A
Artificial Intelligence: Paper Time

Rahil Parikh, Harshavardhan Sundar, Ming Sun, Chao Wang, Spyros MatsoukasAbstractAcoustic events are sounds with well-defined spectro-temporal characteristics which can be associated with the physical objects generating them. Acoustic scenes are collections of such acoustic events in no specific temporal order. Given this natural linkage between ev…
A
Artificial Intelligence: Paper Time

Jiawei ZhangAbstractBrain graph representation learning serves as the fundamental technique for brain diseases diagnosis. Great efforts from both the academic and industrial communities have been devoted to brain graph representation learning in recent years. The isomorphic neural network (IsoNN) introduced recently can automatically learn the exis…
A
Artificial Intelligence: Paper Time

Haoyi Niu, Shubham Sharma, Yiwen Qiu, Ming Li, Guyue Zhou, Jianming Hu, Xianyuan ZhanAbstractLearning effective reinforcement learning (RL) policies to solve real-world complex tasks can be quite challenging without a high-fidelity simulation environment. In most cases, we are only given imperfect simulators with simplified dynamics, which inevitab…
Jacob P. Portes, Christian Schmid, James M. MurrayAbstractDespite extensive theoretical work on biologically plausible learning rules, it has been difficult to obtain clear evidence about whether and how such rules are implemented in the brain. We consider biologically plausible supervised- and reinforcement-learning rules and ask whether changes i…
A
Artificial Intelligence: Paper Time

1
EMVLight: a Multi-agent Reinforcement Learning Framework for an Emergency Vehicle Decentralized Routing and Traffic Signal Control System
Haoran Su, Yaofeng D. Zhong, Joseph Y.J. Chow, Biswadip Dey, Li JinAbstractEmergency vehicles (EMVs) play a crucial role in responding to time-critical calls such as medical emergencies and fire outbreaks in urban areas. Existing methods for EMV dispatch typically optimize routes based on historical traffic-flow data and design traffic signal pre-e…
A
Artificial Intelligence: Paper Time

1
Interpretable Hidden Markov Model-Based Deep Reinforcement Learning Hierarchical Framework for Predictive Maintenance of Turbofan Engines
Ammar N. Abbas, Georgios Chasparis, and John D. KelleherAbstractAn open research question in deep reinforcement learning is how to focus the policy learning of key decisions within a sparse domain. This paper emphasizes combining the advantages of inputoutput hidden Markov models and reinforcement learning towards interpretable maintenance decision…
A
Artificial Intelligence: Paper Time

Taejun Bak, Junmo Lee, Hanbin Bae, Jinhyeok Yang, Jae-Sung Bae, Young-Sun JooAbstractNeural vocoders based on the generative adversarial neural network (GAN) have been widely used due to their fast inference speed and lightweight networks while generating high-quality speech waveforms. Since the perceptually important speech components are primaril…
Bruno Casella, Alessio Barbaro Chisari, Sebastiano Battiato, Mario Valerio GiuffridaAbstractIt has been demonstrated that deep neural networks outperform traditional machine learning. However, deep networks lack generalisability, that is, they will not perform as good as in a new (testing) set drawn from a different distribution due to the domain s…
A
Artificial Intelligence: Paper Time

Edward G. A. Henderson, Andrew F. Green, Marcel van Herk, Eliana M. Vasquez OsorioAbstractAutomatic segmentation of organs-at-risk (OARs) in CT scans using convolutional neural networks (CNNs) is being introduced into the radiotherapy workflow. However, these segmentations still require manual editing and approval by clinicians prior to clinical us…
A
Artificial Intelligence: Paper Time

Florent Bartoccioni, \'Eloi Zablocki, Andrei Bursuc, Patrick P\'erez, Matthieu Cord, Karteek AlahariAbstractRecent works in autonomous driving have widely adopted the bird's-eye-view (BEV) semantic map as an intermediate representation of the world. Online prediction of these BEV maps involves non-trivial operations such as multi-camera data extrac…
Hassan Sajjad, Nadir Durrani, Fahim Dalvi, Firoj Alam, Abdul Rafae Khan, Jia XuAbstractWe propose a novel framework ConceptX, to analyze how latent concepts are encoded in representations learned within pre-trained language models. It uses clustering to discover the encoded concepts and explains them by aligning with a large set of human-defined co…
A
Artificial Intelligence: Paper Time

1
Cracking nuts with a sledgehammer: when modern graph neural networks do worse than classical greedy algorithms
Maria Chiara Angelini, Federico Ricci-TersenghiAbstractThe recent work ``Combinatorial Optimization with Physics-Inspired Graph Neural Networks'' [Nat Mach Intell 4 (2022) 367] introduces a physics-inspired unsupervised Graph Neural Network (GNN) to solve combinatorial optimization problems on sparse graphs. To test the performances of these GNNs, …
A
Artificial Intelligence: Paper Time

Diogo Leit\~ao, Pedro Saleiro, M\'ario A.T. Figueiredo, Pedro BizarroAbstractHuman-AI collaboration (HAIC) in decision-making aims to create synergistic teaming between human decision-makers and AI systems. Learning to Defer (L2D) has been presented as a promising framework to determine who among humans and AI should take which decisions in order t…
Yifan Hou, Hongzhi Chen, Changji Li, James Cheng, Ming-Chang YangAbstractRepresentation learning on graphs, also called graph embedding, has demonstrated its significant impact on a series of machine learning applications such as classification, prediction and recommendation. However, existing work has largely ignored the rich information contained…
Hiroyuki KidoAbstractAn increasing number of scientific experiments support the view of perception as Bayesian inference, which is rooted in Helmholtz's view of perception as unconscious inference. Recent study of logic presents a view of logical reasoning as Bayesian inference. In this paper, we give a simple probabilistic model that is applicable…
A
Artificial Intelligence: Paper Time

Yifan Hou, Jian Zhang, James Cheng, Kaili Ma, Richard T. B. Ma, Hongzhi Chen, Ming-Chang YangAbstractGraph neural networks (GNNs) have been widely used for representation learning on graph data. However, there is limited understanding on how much performance GNNs actually gain from graph data. This paper introduces a context-surrounding GNN framewo…
A
Artificial Intelligence: Paper Time

Ningyuan Huang and Yash R. Deshpande and Yibo Liu and Houda Alberts and Kyunghyun Cho and Clara Vania and Iacer CalixtoAbstractWe propose a method to make natural language understanding models more parameter efficient by storing knowledge in an external knowledge graph (KG) and retrieving from this KG using a dense index. Given (possibly multilingu…
A
Artificial Intelligence: Paper Time

Yurong Chen, Xiaotie Deng, Yuhao LiAbstractTo take advantage of strategy commitment, a useful tactic of playing games, a leader must learn enough information about the follower's payoff function. However, this leaves the follower a chance to provide fake information and influence the final game outcome. Through a carefully contrived payoff function…
A
Artificial Intelligence: Paper Time

Nicos IsaakAbstractThe Taboo Challenge competition, a task based on the well-known Taboo game, has been proposed to stimulate research in the AI field. The challenge requires building systems able to comprehend the implied inferences between the exchanged messages of guesser and describer agents. A describer sends pre-determined hints to guessers i…
A
Artificial Intelligence: Paper Time

Christina Baek, Yiding Jiang, Aditi Raghunathan, Zico KolterAbstractRecently, Miller et al. showed that a model's in-distribution (ID) accuracy has a strong linear correlation with its out-of-distribution (OOD) accuracy on several OOD benchmarks -- a phenomenon they dubbed ''accuracy-on-the-line''. While a useful tool for model selection (i.e., the…
Zhechen Li, Ao Liu, Lirong Xia, Yongzhi Cao, Hanpin WangAbstractDesigning private voting rules is an important and pressing problem for trustworthy democracy. In this paper, under the framework of differential privacy, we propose three classes of randomized voting rules based on the well-known Condorcet method: Laplacian Condorcet method ($CM^{LAP}…
A
Artificial Intelligence: Paper Time

Meirui Jiang, Hongzheng Yang, Xiaoxiao Li, Quande Liu, Pheng-Ann Heng, Qi DouAbstractDespite recent progress on semi-supervised federated learning (FL) for medical image diagnosis, the problem of imbalanced class distributions among unlabeled clients is still unsolved for real-world use. In this paper, we study a practical yet challenging problem o…
A
Artificial Intelligence: Paper Time

Allen Z. Ren, Bharat Govil, Tsung-Yen Yang, Karthik Narasimhan, Anirudha MajumdarAbstractRobust and generalized tool manipulation requires an understanding of the properties and affordances of different tools. We investigate whether linguistic information about a tool (e.g., its geometry, common uses) can help control policies adapt faster to new t…
A
Artificial Intelligence: Paper Time

Jayakanth Kunhoth, Somaya Al-Maadeed, Suchithra Kunhoth, and Younus AkbariAbstractLearning disabilities, which primarily interfere with the basic learning skills such as reading, writing and math, are known to affect around 10% of children in the world. The poor motor skills and motor coordination as part of the neurodevelopmental disorder can beco…
Jiaming Song, Lantao Yu, Willie Neiswanger, Stefano ErmonAbstractThe acquisition function, a critical component in Bayesian optimization (BO), can often be written as the expectation of a utility function under a surrogate model. However, to ensure that acquisition functions are tractable to optimize, restrictions must be placed on the surrogate mo…
Mohammed Adnan, Yani Ioannou, Chuan-Yung Tsai, Angus Galloway, H.R. Tizhoosh, Graham W. TaylorAbstractThe failure of deep neural networks to generalize to out-of-distribution data is a well-known problem and raises concerns about the deployment of trained networks in safety-critical domains such as healthcare, finance and autonomous vehicles. We st…
A
Artificial Intelligence: Paper Time

Chuang Zhang, Li Shen, Jian Yang, Chen GongAbstractThe memorization effect of deep neural networks (DNNs) plays a pivotal role in recent label noise learning methods. To exploit this effect, the model prediction-based methods have been widely adopted, which aim to exploit the outputs of DNNs in the early stage of learning to correct noisy labels. H…
A
Artificial Intelligence: Paper Time

Peng Zhou, Jason K. Eshraghian, Dong-Uk Choi, Wei D. Lu, Sung-Mo KangAbstractWe present MEMprop, the adoption of gradient-based learning to train fully memristive spiking neural networks (MSNNs). Our approach harnesses intrinsic device dynamics to trigger naturally arising voltage spikes. These spikes emitted by memristive dynamics are analog in na…
A
Artificial Intelligence: Paper Time

Shurui Gui, Hao Yuan, Jie Wang, Qicheng Lao, Kang Li, Shuiwang JiAbstractWe investigate the explainability of graph neural networks (GNNs) as a step towards elucidating their working mechanisms. While most current methods focus on explaining graph nodes, edges, or features, we argue that, as the inherent functional mechanism of GNNs, message flows …
Kailash Budhathoki, George Michailidis, Dominik JanzingAbstractExisting methods of explainable AI and interpretable ML cannot explain change in the values of an output variable for a statistical unit in terms of the change in the input values and the change in the "mechanism" (the function transforming input to output). We propose two methods based…
A
Artificial Intelligence: Paper Time

Sabrina J. Mielke, Arthur Szlam, Emily Dinan, Y-Lan BoureauAbstractWhile improving neural dialogue agents' factual accuracy is the object of much research, another important aspect of communication, less studied in the setting of neural dialogue, is transparency about ignorance. In this work, we analyze to what extent state-of-the-art chit-chat mod…
Johannes Schneider and Rene Abraham and Christian Meske and Jan vom BrockeAbstractArtificial Intelligence (AI) governance regulates the exercise of authority and control over the management of AI. It aims at leveraging AI through effective use of data and minimization of AI-related cost and risk. While topics such as AI governance and AI ethics are…
Chao Huang, Jianwei Huang, Xin LiuAbstractFederated learning (FL) is an emerging technology that enables the training of machine learning models from multiple clients while keeping the data distributed and private. Based on the participating clients and the model training scale, federated learning can be classified into two types: cross-device FL w…
A
Artificial Intelligence: Paper Time

Fabio Aurelio D'Asaro, Giuseppe PrimieroAbstractIn this paper we present the probabilistic typed natural deduction calculus TPTND, designed to reason about and derive trustworthiness properties of probabilistic computational processes, like those underlying current AI applications. Derivability in TPTND is interpreted as the process of extracting $…
A
Artificial Intelligence: Paper Time

Marco Forgione, Manas Mejari, Dario PigaAbstractIn recent years, several algorithms for system identification with neural state-space models have been introduced. Most of the proposed approaches are aimed at reducing the computational complexity of the learning problem, by splitting the optimization over short sub-sequences extracted from a longer …
A
Artificial Intelligence: Paper Time

Jaeyun Song, Joonhyung Park, Eunho YangAbstractLearning unbiased node representations under class-imbalanced graph data is challenging due to interactions between adjacent nodes. Existing studies have in common that they compensate the minor class nodes `as a group' according to their overall quantity (ignoring node connections in graph), which ine…
A
Artificial Intelligence: Paper Time

Xiongjie Chen, Yunpeng Li, Yongxin YangAbstractOut-of-distribution (OOD) detection has recently received much attention from the machine learning community due to its importance in deploying machine learning models in real-world applications. In this paper we propose an uncertainty quantification approach by modelling the distribution of features. …