2005년 대한 생화학·분자생물학회 하계학술대회를 다녀와서

When building a unified vision system or gradually adding new capabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new capabilities to a Convolutional Neural Network (CNN), but the training data for its existing capabilities are unavailable. We propose our Learning without Forgetting method, which uses only new task data to train the network while preserving the original capabilities. Our method performs favorably compared to commonly used feature extraction and fine-tuning adaption techniques and performs similarly to multitask learning that uses original task data we assume unavailable. A more surprising observation is that Learning without Forgetting may be able to replace fine-tuning with similar old and new task datasets for improved new task performance.

Learning without Forgetting

Since the popularisation of the Internet in the 1990s, the cyberspace has kept evolving. We have created various computer-mediated virtual environments including social networks, video conferencing, virtual 3D worlds (e.g., VR Chat), augmented reality applications (e.g., Pokemon Go), and Non-Fungible Token Games (e.g., Upland). Such virtual environments, albeit non-perpetual and unconnected, have bought us various degrees of digital transformation. The term `metaverse' has been coined to further facilitate the digital transformation in every aspect of our physical lives. At the core of the metaverse stands the vision of an immersive Internet as a gigantic, unified, persistent, and shared realm. While the metaverse may seem futuristic, catalysed by emerging technologies such as Extended Reality, 5G, and Artificial Intelligence, the digital `big bang' of our cyberspace is not far away. This survey paper presents the first effort to offer a comprehensive framework that examines the latest metaverse development under the dimensions of state-of-the-art technologies and metaverse ecosystems, and illustrates the possibility of the digital `big bang'. First, technologies are the enablers that drive the transition from the current Internet to the metaverse. We thus examine eight enabling technologies rigorously - Extended Reality, User Interactivity (Human-Computer Interaction), Artificial Intelligence, Blockchain, Computer Vision, IoT and Robotics, Edge and Cloud computing, and Future Mobile Networks. In terms of applications, the metaverse ecosystem allows human users to live and play within a self-sustaining, persistent, and shared realm. Therefore, we discuss six user-centric factors -- Avatar, Content Creation, Virtual Economy, Social Acceptability, Security and Privacy, and Trust and Accountability. Finally, we propose a concrete research agenda for the development of the metaverse.

All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda

The Internet of Things (IoT) is penetrating many facets of our daily life with the proliferation of intelligent services and applications empowered by artificial intelligence (AI). Traditionally, AI techniques require centralized data collection and processing that may not be feasible in realistic application scenarios due to the high scalability of modern IoT networks and growing data privacy concerns. Federated Learning (FL) has emerged as a distributed collaborative AI approach that can enable many intelligent IoT applications, by allowing for AI training at distributed IoT devices without the need for data sharing. In this article, we provide a comprehensive survey of the emerging applications of FL in IoT networks, beginning from an introduction to the recent advances in FL and IoT to a discussion of their integration. Particularly, we explore and analyze the potential of FL for enabling a wide range of IoT services, including IoT data sharing, data offloading and caching, attack detection, localization, mobile crowdsensing, and IoT privacy and security. We then provide an extensive survey of the use of FL in various key IoT applications such as smart healthcare, smart transportation, Unmanned Aerial Vehicles (UAVs), smart cities, and smart industry. The important lessons learned from this review of the FL-IoT services and applications are also highlighted. We complete this survey by highlighting the current challenges and possible directions for future research in this booming area.

/pdf/federated-learning-for-internet-of-things-a-comprehensive-3ttswrbjdg.pdf

Federated Learning for Internet of Things: A Comprehensive Survey

Metaverse beyond the hype: Multidisciplinary perspectives on emerging challenges, opportunities, and agenda for research, practice and policy

The era of pervasive computing has resulted in countless devices that continuously monitor users and their environment, generating an abundance of user behavioural data. Such data may support improving the quality of service, but may also lead to adverse usages such as surveillance and advertisement. In parallel, Artificial Intelligence (AI) systems are being applied to sensitive fields such as healthcare, justice, or human resources, raising multiple concerns on the trustworthiness of such systems. Trust in AI systems is thus intrinsically linked to ethics, including the ethics of algorithms, the ethics of data, or the ethics of practice. In this paper, we formalise the requirements of trustworthy AI systems through an ethics perspective. We specifically focus on the aspects that can be integrated into the design and development of AI systems. After discussing the state of research and the remaining challenges, we show how a concrete use-case in smart cities can benefit from these methods.

Trustworthy AI in the Age of Pervasive Computing and Big Data

Continual learning approaches help deep neural network models adapt and learn incrementally by trying to solve catastrophic forgetting. However, whether these existing approaches, applied traditionally to image-based tasks, work with the same efficacy to the sequential time series data generated by mobile or embedded sensing systems remains an unanswered question. 
To address this void, we conduct the first comprehensive empirical study that quantifies the performance of three predominant continual learning schemes (i.e., regularization, replay, and replay with examples) on six datasets from three mobile and embedded sensing applications in a range of scenarios having different learning complexities. More specifically, we implement an end-to-end continual learning framework on edge devices. Then we investigate the generalizability, trade-offs between performance, storage, computational costs, and memory footprint of different continual learning methods. 
Our findings suggest that replay with exemplars-based schemes such as iCaRL has the best performance trade-offs, even in complex scenarios, at the expense of some storage space (few MBs) for training examples (1% to 5%). We also demonstrate for the first time that it is feasible and practical to run continual learning on-device with a limited memory budget. In particular, the latency on two types of mobile and embedded devices suggests that both incremental learning time (few seconds - 4 minutes) and training time (1 - 75 minutes) across datasets are acceptable, as training could happen on the device when the embedded device is charging thereby ensuring complete data privacy. Finally, we present some guidelines for practitioners who want to apply a continual learning paradigm for mobile sensing tasks.

Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications

Artificial intelligence shows promise for solving many practical societal problems in areas such as healthcare and transportation. However, the current mechanisms for AI model diffusion such as Github code repositories, academic project webpages, and commercial AI marketplaces have some limitations; for example, a lack of monetization methods, model traceability, and model auditabilty. In this work, we sketch guidelines for a new AI diffusion method based on a decentralized online marketplace. We consider the technical, economic, and regulatory aspects of such a marketplace including a discussion of solutions for problems in these areas. Finally, we include a comparative analysis of several current AI marketplaces that are already available or in development. We find that most of these marketplaces are centralized commercial marketplaces with relatively few models.

/pdf/sketching-an-ai-marketplace-tech-economic-and-regulatory-3i19ddahww.pdf

Abhishek Kumar

Papers

All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda

Trustworthy AI in the Age of Pervasive Computing and Big Data

Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications

Sketching an AI Marketplace: Tech, Economic, and Regulatory Aspects

Marketplace for AI Models