Ke Chen

The University of Manchester · Department of Computer Science

Feature importance ranking has become a powerful tool for explainable AI. However, its nature of combinatorial optimization poses a great challenge for deep learning. In this paper, we propose a novel dual-net architecture consisting of operator and selector for discovery of an optimal feature subset of a fixed size and ranking the importance of th...

Multi-label classification has attracted increasing attention in various applications, such as medical diagnosis and semantic annotation. With such trend, a large number of ensemble approaches have been proposed for multi-label classification tasks. Most of these approaches construct the ensemble members by using bagging schemes, butfew stacked ens...

While learning models are typically studied for inputs in the form of a fixed dimensional feature vector, real world data is rarely found in this form. In order to meet the basic requirement of traditional learning models, structural data generally have to be converted into fix-length vectors in a handcrafted manner, which is tedious and may even i...

Transcription factors (TFs) can bind DNA in a cooperative manner, enabling a mutual increase in occupancy. Through this type of interaction, alternative binding sites can be preferentially bound in different tissues to regulate tissue-specific expression programmes. Recently, deep learning models have become state-of-the-art in various pattern anal...

In this paper we examine a formalization of feature distribution learning (FDL) in information-theoretic terms relying on the analytical approach and on the tools already used in the study of the information bottleneck (IB). It has been conjectured that the behavior of FDL algorithms could be expressed as an optimization problem over two informatio...

One of the major challenges in person Re-Identification (ReID) is the inconsistent visual appearance of a person. Current works on visual feature and distance metric learning have achieved significant achievements, but still suffer from the limited robustness to pose variations, viewpoint changes, etc. This makes person ReID among multiple cameras...

In general, video games not only prevail in entertainment but also have become an alternative methodology for knowledge learning, skill acquisition and assistance for medical treatment as well as health care in education, vocational/military training and medicine. On the other hand, video games also provide an ideal test bed for AI researches. To a...

Motivation: Transcription factors (TFs) can bind DNA in a cooperative manner, enabling a mutual increase in occupancy. Through this type of interaction, alternative binding sites can be preferentially bound in different tissues to regulate tissue-specific expression programmes. Recently, deep learning models have become state-of-the-art in various...

Deep reinforcement learning (DRL) has proven to be an effective tool for creating general video-game AI. However most current DRL video-game agents learn end-to-end from the video-output of the game, which is superfluous for many applications and creates a number of additional problems. More importantly, directly working on pixel-based raw video da...

Deep reinforcement learning (DRL) has proven to be an effective tool for creating general video-game AI. However most current DRL video-game agents learn end-to-end from the video-output of the game, which is superfluous for many applications and creates a number of additional problems. More importantly, directly working on pixel-based raw video da...

Deep reinforcement learning (DRL) has proven to be an effective tool for creating general video-game AI. However most current DRL video-game agents learn end-to-end from the video-output of the game, which is superfluous for many applications and creates a number of additional problems. More importantly, directly working on pixel-based raw video da...

Human action recognition refers to automatic recognizing human actions from a video clip, which is one of the most challenging tasks in computer vision. In reality, a video stream is often weakly-annotated with a set of relevant human action labels at a global level rather than assigning each label to a specific video episode corresponding to a sin...

Zero-shot learning for visual recognition, e.g., object and action recognition, has recently attracted a lot of attention. However, it still remains challenging in bridging the semantic gap between visual features and their underlying semantics and transferring knowledge to semantic categories unseen during learning. Unlike most of the existing met...

Computational cognitive models of spatial memory often neglect difficulties posed by the real world, such as sensory noise, uncertainty, and high spatial complexity. On the other hand, robotics is unconcerned with understanding biological cognition. Here, we describe a computational framework for robotic architectures aiming to function in realisti...

Among the main challenges in procedural content generation (PCG), content quality assurance and dynamic difficulty adjustment (DDA) of game content in real time are two major issues concerned in adaptive content generation. Motivated by the recent learning-based PCG framework, we propose a novel approach to seamlessly address two issues in Super Ma...

A proper semantic representation for encoding side information is key to the success of zero-shot learning. In this paper, we explore two alternative semantic representations especially for zero-shot human action recognition: textual descriptions of human actions and deep features extracted from still images relevant to human actions. Such side inf...

Guiding representation learning towards temporally stable features improves object identity encoding from video. Existing models have applied temporal coherence uniformly over all features based on the assumption that optimal object identity encoding only requires temporally stable components. We explore the effects of mixing temporally coherent in...

The ultimate goals of serious educational games (SEG) are to facilitate learning and maximizing enjoyment during playing SEGs. In SEG development, there are normally two spaces to be taken into account: knowledge space regarding learning materials and content space regarding games to be used to convey learning materials. How to deploy the learning...

A major challenge in machine learning is covariate shift, i.e., the problem of training data and test data coming from different distributions. This paper studies the feasibility of tackling this problem by means of sparse filtering. We show that the sparse filtering algorithm intrinsically addresses this problem, but it has limited capacity for co...

It has been suggested that the map-like representations that support human spatial memory are fragmented into sub-maps with local reference frames, rather than being unitary and global. However, the principles underlying the structure of these 'cognitive maps' are not well understood. We propose that the structure of the representations of navigati...

Methodological details. (PDF)

Zero Shot Learning (ZSL) enables a learning model to classify instances of an unseen class during training. While most research in ZSL focuses on single-label classification, few studies have been done in multi-label ZSL, where an instance is associated with a set of labels simultaneously, due to the difficulty in modeling complex semantics conveye...

Purpose The use of mobile devices in handling our daily activities that involve the storage or access of sensitive data (e.g. on-line banking, paperless prescription services, etc.) is becoming very common. These mobile electronic services typically use a knowledge-based authentication method to authenticate a user (claimed identity). However, this...

In this paper we present our study on a recent and effective algorithm for unsupervised learning, that is, sparse filtering. The aim of this research is not to show whether or how well sparse filtering works, but to understand why and when sparse filtering does work. We provide a thorough study of this algorithm through a conceptual evaluation of f...

The ability to represent and utilize spatial information relevant to their goals is vital for intelligent agents. Doing so in the real world presents significant challenges, which have so far mostly been addressed by robotics approaches neglecting cognitive plausibility; whereas existing cognitive models mostly implement spatial abilities in simpli...

There have been research activities in the area of keystroke dynamics biometrics on physical keyboards (desktop computers or conventional mobile phones) undertaken in the past three decades. However, in terms of touch dynamics biometrics on virtual keyboards (modern touchscreen mobile devices), there has been little published work. Particularly, th...

Mobile devices have become an integral part of our routine activities. Some of the activities involve the storage or access of sensitive data (e.g. on-line banking, paperless prescription services, etc.). These mobile electronic services (e-Services) typically require a method to securely identify and authenticate a claimed identity. Currently, e-S...

Procedural content generation (PCG) is of great interest to game design and development as it generates game content automatically. Motivated by the recent learning-based PCG framework and other existing PCG works, we propose an alternative approach to online content generation and adaptation in Super Mario Bros (SMB). Unlike most of existing works...

Accurate spatial localization requires a mechanism that corrects for errors, which might arise from inaccurate sensory information or neuronal noise. In this paper, we propose that Hippocampal place cells might implement such an error correction mechanism by integrating different sources of information in an approximately Bayes-optimal fashion. We...

One of the biggest challenges in Multimedia information retrieval and understanding is to bridge the semantic gap by properly modeling concept semantics in context. The presence of out of vocabulary (OOV) concepts exacerbates this difficulty. To address the semantic gap issues, we formulate a problem on learning contextualized semantics from descri...

Spatial memory refers to the part of the memory system that encodes, stores, recognizes and recalls spatial information about the environment and the agent’s orientation within it. Such information is required to be able to navigate to goal locations, and is vitally important for any embodied agent, or model thereof, for reaching goals in a spatial...

Automatic annotation of music with tags is a promising methodology for the acquisition of semantics that facilitates music information retrieval and understanding. One of the biggest challenges for this methodology is modeling concept semantics in context. Moreover, the out of vocabulary (OOV) problem exacerbates its difficulty and has yet to be ad...

Procedural content generation (PCG) has recently become one of the hottest topics in computational intelligence and AI game research. While some substantial progress has been made in this area, there are still several challenges ranging from content evaluation to personalized content generation. In this paper, we present a novel PCG framework based...

Various aspects of computer game design, including adaptive elements of game levels, characteristics of 'bot' behavior, and player matching in multiplayer games, would ideally be sensitive to a player's skill level. Yet, while difficulty and player learning have been explored in the context of games, there has been little work analyzing skill per s...

Accurate spatial localization requires a mechanism that corrects for errors, which might arise from inaccurate sensory information or neuronal noise. In this paper, we propose that Hippocampal place cells might implement such an error correction mechanism by integrating different sources of information in an approximately Bayes-optimal fashion. We...

One way to make video games more attractive to a wider audience is to make them adaptive to players. The preferences and skills of players can be determined in a variety of ways, but should be done as unobtrusively as possible to keep the player immersed. This paper explores how gameplay input recorded in a first-person shooter can predict a player...

Human spatial representations are known to be remarkably robust and efficient, and to be structured hierarchically. In this paper, we describe a biologically inspired computational model of spatial working memory attempting to account for these properties, based on the LIDA cognitive architecture. We also present preliminary results regarding a virt...

Speech signals convey various yet mixed information ranging from linguistic to speaker-specific information. However, most of acoustic representations characterize all different kinds of information as whole, which could hinder either a speech or a speaker recognition (SR) system from producing a better performance. In this paper, we propose a nove...

 Abstract—This paper presents our investigations on automatic emotional state recognition from speech signals using ensemble based methods based on different acoustic representations/feature measures. In our work, we employ various types of acoustic feature measures where none of the feature measures is optimal for emotional state classification....

Speech signals convey different types of information which vary from linguistic to speaker-specific and should be used in different tasks. However, it is hard to extract a special type of information such that nearly all acoustic representations of speech present all kinds of information as a whole. The use of the same representation in different t...

Temporal data clustering provides underpinning techniques for discovering the intrinsic structure and condensing information over temporal data. In this paper, we present a temporal data clustering framework via a weighted clustering ensemble of multiple partitions produced by initial clustering analysis on different temporal data representations....

This paper presents our investigations on emotional state categorization from speech signals with a psychologically inspired computational model against human performance under the same experimental setup. Based on psychological studies, we propose a multistage categorization strategy which allows establishing an automatic categorization model flex...

We propose a novel feature selection strategy to discover language-independent acoustic features that tend to be responsible for emotions regardless of languages, linguistics and other factors. Experimental results suggest that the language-independent feature subset discovered yields the performance comparable to the full feature set on various em...

Unsupervised classification or clustering is an important data analysis technique demanded in various fields including machine learning, data mining, pattern recognition, image analysis and bioinformatics. Recently a large number of studies have attempted to improve clustering by combing multiple clustering solutions into a single consolidated clus...

N/A

This paper investigates the performance of automatic emotional state categorization from speech signals on the Serbian Emotional Speech Corpus, named GEES, against the corresponding human performance. We employ a multistage strategy along with sophisticated features used for automatic emotional state categorization. Our study is the first attempt t...

Unlike traditional pattern classification, semi-supervised learning provides a novel technique to make use of both labeled and unlabeled data for improving the performance of classification. In general, there are two critical issues for semi-supervised learning of discriminative classifiers; i.e., how to create an initial classifier of a good gener...

Semi-supervised inductive learning concerns how to learn a decision rule from a data set containing both labeled and unlabeled data. Several boosting algorithms have been extended to semi-supervised learning with various strategies. To our knowledge, however, none of them takes local smoothness constraints among data into account during ensemble le...

Hyperbolic Function Networks for Pattern Classification.- Variable Selection for the Linear Support Vector Machine.- Selecting Data for Fast Support Vector Machines Training.- Universal Approach to Study Delayed Dynamical Systems.- A Hippocampus-Neocortex Model for Chaotic Association.- Latent Attractors: A General Paradigm for Context-Dependent Ne...

Sequential data clustering provides useful techniques for condensing and summarizing information conveyed in sequential data, which is demanded in various fields ranging from time series analysis to video clip understanding. In this chapter, we propose a novel approach to sequential data clustering by combining multiple competitive learning network...

Relev ance feedback is an efiective scheme bridging the gap between high-level semantics and low- level features in content-based image retrieval (Cbir). In contrast to previous methods which rely on labeled images provided by the user, this paper attempts to enhance the performance of relevance feedback by exploiting unlabeled images existing in t...

Temporal data clustering provides useful techniques for condensing and summarizing information conveyed in temporal data, which is demanded in various fields ranging from time series analysis to sequential data understanding. In this paper, we propose a novel approach to temporal data clustering by an ensemble of competitive learning networks incor...

A novel adaptive smoothing approach is proposed for noise removal and feature preservation where two distinct measures are simultaneously adopted to detect discontinuities in an image. Inhomogeneity underlying an image is employed as a multiscale measure to detect contextual discontinuities for feature preservation and control of the smoothing spee...

Numerous speech representations have been reported to be useful in speaker recognition. However, there is much less agreement on which speech representation provides a perfect representation of speaker-specific information conveyed in a speech signal. Unlike previous work, we propose an alternative approach to speaker modeling by the simultaneous u...

Input/output hidden Markov model (IOHMM) has turned out to be effective in sequential data processing via supervised learning. However, there are several difficulties, e.g. model selection, unexpected local optima and high computational complexity, which hinder an IOHMM from yielding the satisfactory performance in sequence classification. Unlike p...