The 9th International Conference on Brain-Inspired Cognitive System
The 9th International Conference on Brain Inspired Cognitive Systems (BICS 2018) will be held in Xi’an, China, as a sequel of BICS 2004 - 2016. It is co-organised by Northwestern Polytechnical University (www.nwpu.edu.cn) and The Guangzhou Key Laboratory of Digital Content Processing and Security Technologies University (www.gpnu.edu.cn).
Geographically located at the heart of China, Xi’an is the capital and largest city of Shaanxi Province. It once served as the capital city of ancient China for 13 dynasties, with a history of 5,000 years. Xi’an witnessed the most glorious history of China, and now ranks as one of the top 10 tourist destinations in China with a distinctive culture. Xi'an is the starting point of the Silk Road and home to the Terracotta Army of Emperor Qin Shi Huang, the first Emperor in Chinese history.
BICS 2018 aims to provide a high-level international forum for scientists, engineers, and educators to present the state of the art of brain inspired cognitive systems research and applications in diverse fields. The conference will feature plenary lectures given by world renowned scholars, regular sessions with broad coverage, and some special sessions and workshops focusing on popular and timely topics.
BICS’2018 conference proceedings will be published as part of Springer LNAI Series and indexed by EI. Selected papers will be published in a special issue of the leading (ISI SCI indexed) Springer journal: Cognitive Computation Journal (http://springer.com/12559 - current ISI Impact Factor: 3.44).and/or IJAC(International Journal of Automation and Computing, https://link.springer.com/journal/11633, http://www.ijac.net).
Psychiatry, UC-San Francisco, USA.
Director of Clinical Program/Neuroscape and Digital Health Core, in the Dept. of Neurology and Psychiatry, UC-San Francisco, USA.
Dr. Anguera’s work leverages state-of-the-art technological approaches to create (i) advanced training tools to remediate cognitive deficiencies and (ii) use mobile technology to robustly characterizing individual abilities outside of the laboratory.
Using EEG to quantify the enhancement of cognitive control deficits in older adults following video game training
Cognitive control is defined as those (neural) processes that facilitate interacting with our environment in a goal-directed manner. Here we asked whether age-related cognitive control deficits measured with electroencephalography (EEG) could be remediated by training with a custom-designed video game (Anguera et al., 2013; Nature). I will discuss quantifying these findings by describing the step-by-step EEG collection and analysis efforts that generated event-related spectral perturbations (ERSP) and long-range phase coherence time-locked to the onset of each stimulus presented. This data set provides evidence of how EEG can be used to evaluate underlying neural mechanisms associated with cognitive enhancement efforts.
Professor, Xi'an Jiaotong-Liverpool University, China
Kaizhu Huang is currently a Professor and Head, Department of Electrical and Electronic Engineering, Xi’an Jiaotong-Liverpool University, China. He is also the founding director of Suzhou Municipal Key Laboratory of Cognitive Computation and Applied Technology.
Prof. Huang has been working in machine learning, neural information processing, and pattern recognition. He was the recipient of 2011 Asia Pacific Neural Network Society (APNNS) Younger Researcher Award. He also received Best Book Award in National Three 100 Competition 2009. He has published 8 books in Springer and over 120 international research papers (50+ SCI-indexed international journals and 50+ EI conference papers).
Learning adversarial examples for robust pattern recognition
Adversarial examples are augmented data points generated by imperceptible perturbation of input samples. They have recently drawn much attention with the machine learning community. Being difficult to distinguish from real examples, such adversarial examples could change the prediction of many of the best machine learning models including the state-of-the-art deep learning models. Recent attempts have been made to build robust models that take into account adversarial examples. However, these methods can either lead to performance drops, or are ad-hoc in nature and lack mathematic motivations. In this talk, we propose a unified framework to build robust machine learning models against adversarial examples. More specifically, using the unified framework, we develop a family of gradient regularization methods that effectively penalize the gradient of loss function w.r.t. inputs. Importantly, such gradient regularization terms are shown highly robust to perturbations both theoretically and empirically. Our proposed framework is appealing in that it offers a unified view to deal with adversarial examples. It incorporates another recently-proposed famous perturbation based approach as a special case. In addition, we make both theoretical and empirical analysis on adversarial examples and present some visual effects that are not deemed to exist. By applying this technique to deep learning networks, we conduct a series of experiments and achieve encouraging results.
Professor, University of Technology, Sydney, Australia
Professor Sean He, as a Chief Investigator, has received various research grants including four national Research Grants awarded by Australian Research Council (ARC). He is the Director of Computer Vision and Pattern Recognition Laboratory at the Global Big Data Technologies Centre (GBDTC). He is also the Director of UTS-NPU International Joint Laboratory on Digital Media and Intelligent Networks. He is an IEEE Senior Member and has been an IEEE Signal Processing Society Student Committee member. He is a leading researcher in several research areas including big-learning based human behaviors recognition on a single image, image processing based on hexagonal structure, authorship identification of a document and a document’s components (e.g., sentences, sections etc.), network intrusion detection using computer vision techniques, car license plate recognition of high speed moving vehicles with changeable and complex background, and video tracking with motion blur. He has played various chair roles in many international conferences such as ACM MM, MMM, IEEE BigDataSE, IEEE CIT, IEEE AVSS, IEEE TrustCom, IEEE ICPR and IEEE ICARCV. In recent years, he has many high quality publications in IEEE Transactions journals such as IEEE Transactions on Mobile Computing, IEEE Transactions on Computers, IEEE Transactions on Parallel and Distributed Systems, and IEEE Transactions on Multimedia; and in Elsevier’s journals such as Pattern Recognition, Signal Processing, and Computer Networks. He has also had papers published in premier international conferences and workshops such as ACL, IJCAI, CVPR, ECCV and ACM MM.
Classification of Parkinson’s Disease
Parkinson’s disease (PD) is a degenerative disorder that affects the parts of the brain that controls movements and coordination. As a result a person might face difficulty in moving along with symptoms like automatic shaking movement of body, arm, lip and hands. After diagnosis, Parkinson disease treatments are given to help relieve the symptoms. However there are cases in which the symptoms are so severe that surgery is required for the patient. This talk introduces a model to classify patients with Parkinson disease on determining whether a patient requires surgery or not. It will assist medical professionals in diagnosing PD for delivering the right treatment on PD patients.
Professor, Hundred Talents Program at the National Lab of Pattern Recognition CASIA, China
Prof. Liang Wang received both the BEng and MEng degrees from Anhui University, in 1997 and 2000, respectively, and the PhD degree from the Institute of Automation, Chinese Academy of Sciences (CASIA), in 2004. From 2004 to 2010, he was a research assistant at Imperial College London, United Kingdom, and Monash University, Australia, a research fellow with the University of Melbourne, Australia, and a lecturer with the University of Bath, United Kingdom, respectively. Currently, he is a full professor of the Hundred Talents Program at the National Lab of Pattern Recognition, CASIA. His major research interests include machine learning, pattern recognition, and computer vision. He has widely published in highly ranked international journals such as the IEEE TPAMI and the IEEE TIP, and leading international conferences such as CVPR, ICCV, and ICDM. He is a senior member of the IEEE and a fellow of the IAPR.
Deep Cognitive Networks and Their Visual Applications
Deep neural networks have achieved great success in a wide range of applications. However, there still exists a huge performance gap between the best deep model and human cognitive system. Unlike human cognitive (e.g., visual) system, the current best deep model still cannot reliably guide blind people across the street. Although the current deep models can effectively implement the nonlinear mappings from information perception to primary decision, they ignore to model the higher-level cognitive mechanisms, which are usually regarded to play essential roles during information processing. This talk will introduce our recent work on deep modeling of key cognitive mechanisms such as attention and memory from neuroscience, called deep cognitive networks, as well as their applications in terms of multimodal learning, person re-id and semantic segmentation.