arXiv subjects

Nanning Zheng

Publications and source records attributed to Nanning Zheng.

172 records · Page 10Linked to original sources

arXiv2017

Brain Inspired Cognitive Model with Attention for Self-Driving Cars

Perception-driven approach and end-to-end system are two major vision-based frameworks for self-driving cars. However, it is difficult to introduce attention and historical information of autonomous driving process, which are the essential factors for achieving human-like driving into these two methods. In this paper, we propose a novel model for self-driving cars named brain-inspired cognitive model with attention (CMA). This model consists of three parts: a convolutional neural network for simulating human visual cortex, a cognitive map built to describe relationships between objects in complex traffic scene and a recurrent neural network that combines with the real-time updated cognitive map to implement attention mechanism and long-short term memory. The benefit of our model is that can accurately solve three tasks simultaneously:1) detection of the free space and boundaries of the current and adjacent lanes. 2)estimation of obstacle distance and vehicle attitude, and 3) learning of driving behavior and decision making from human driver. More significantly, the proposed model could accept external navigating instructions during an end-to-end driving process. For evaluation, we build a large-scale road-vehicle dataset which contains more than forty thousand labeled road images captured by three cameras on our self-driving car. Moreover, human driving activities and vehicle states are recorded in the meanwhile.

cs.CV↗

arXiv2017

FASHION: Fault-Aware Self-Healing Intelligent On-chip Network

To avoid packet loss and deadlock scenarios that arise due to faults or power gating in multicore and many-core systems, the network-on-chip needs to possess resilient communication and load-balancing properties. In this work, we introduce the Fashion router, a self-monitoring and self-reconfiguring design that allows for the on-chip network to dynamically adapt to component failures. First, we introduce a distributed intelligence unit, called Self-Awareness Module (SAM), which allows the router to detect permanent component failures and build a network connectivity map. Using local information, SAM adapts to faults, guarantees connectivity and deadlock-free routing inside the maximal connected subgraph and keeps routing tables up-to-date. Next, to reconfigure network links or virtual channels around faulty/power-gated components, we add bidirectional link and unified virtual channel structure features to the Fashion router. This version of the router, named Ex-Fashion, further mitigates the negative system performance impacts, leads to larger maximal connected subgraph and sustains a relatively high degree of fault-tolerance. To support the router, we develop a fault diagnosis and recovery algorithm executed by the Built-In Self-Test, self-monitoring, and self-reconfiguration units at runtime to provide fault-tolerant system functionalities. The Fashion router places no restriction on topology, position or number of faults. It drops 54.3-55.4% fewer nodes for same number of faults (between 30 and 60 faults) in an 8x8 2D-mesh over other state-of-the-art solutions. It is scalable and efficient. The area overheads are 2.311% and 2.659% when implemented in 8x8 and 16x16 2D-meshes using the TSMC 65nm library at 1.38GHz clock frequency.

cs.AR↗

arXiv2016

Robust Learning with Kernel Mean p-Power Error Loss

Correntropy is a second order statistical measure in kernel space, which has been successfully applied in robust learning and signal processing. In this paper, we define a nonsecond order statistical measure in kernel space, called the kernel mean-p power error (KMPE), including the correntropic loss (CLoss) as a special case. Some basic properties of KMPE are presented. In particular, we apply the KMPE to extreme learning machine (ELM) and principal component analysis (PCA), and develop two robust learning algorithms, namely ELM-KMPE and PCA-KMPE. Experimental results on synthetic and benchmark data show that the developed algorithms can achieve consistently better performance when compared with some existing methods.

stat.ML↗

arXiv2016

Counting Grid Aggregation for Event Retrieval and Recognition

Event retrieval and recognition in a large corpus of videos necessitates a holistic fixed-size visual representation at the video clip level that is comprehensive, compact, and yet discriminative. It shall comprehensively aggregate information across relevant video frames, while suppress redundant information, leading to a compact representation that can effectively differentiate among different visual events. In search for such a representation, we propose to build a spatially consistent counting grid model to aggregate together deep features extracted from different video frames. The spatial consistency of the counting grid model is achieved by introducing a prior model estimated from a large corpus of video data. The counting grid model produces an intermediate tensor representation for each video, which automatically identifies and removes the feature redundancy across the different frames. The tensor representation is subsequently reduced to a fixed-size vector representation by averaging over the counting grid. When compared to existing methods on both event retrieval and event classification benchmarks, we achieve significantly better accuracy with much more compact representation.

cs.CV↗

arXiv2016

Kernel Risk-Sensitive Loss: Definition, Properties and Application to Robust Adaptive Filtering

Nonlinear similarity measures defined in kernel space, such as correntropy, can extract higher-order statistics of data and offer potentially significant performance improvement over their linear counterparts especially in non-Gaussian signal processing and machine learning. In this work, we propose a new similarity measure in kernel space, called the kernel risk-sensitive loss (KRSL), and provide some important properties. We apply the KRSL to adaptive filtering and investigate the robustness, and then develop the MKRSL algorithm and analyze the mean square convergence performance. Compared with correntropy, the KRSL can offer a more efficient performance surface, thereby enabling a gradient based method to achieve faster convergence speed and higher accuracy while still maintaining the robustness to outliers. Theoretical analysis results and superior performance of the new algorithm are confirmed by simulation.

stat.ML↗

arXiv2016

Correntropy Maximization via ADMM - Application to Robust Hyperspectral Unmixing

In hyperspectral images, some spectral bands suffer from low signal-to-noise ratio due to noisy acquisition and atmospheric effects, thus requiring robust techniques for the unmixing problem. This paper presents a robust supervised spectral unmixing approach for hyperspectral images. The robustness is achieved by writing the unmixing problem as the maximization of the correntropy criterion subject to the most commonly used constraints. Two unmixing problems are derived: the first problem considers the fully-constrained unmixing, with both the non-negativity and sum-to-one constraints, while the second one deals with the non-negativity and the sparsity-promoting of the abundances. The corresponding optimization problems are solved efficiently using an alternating direction method of multipliers (ADMM) approach. Experiments on synthetic and real hyperspectral images validate the performance of the proposed algorithms for different scenarios, demonstrating that the correntropy-based unmixing is robust to outlier bands.

stat.ML↗

arXiv2015

Generalized Correntropy for Robust Adaptive Filtering

As a robust nonlinear similarity measure in kernel space, correntropy has received increasing attention in domains of machine learning and signal processing. In particular, the maximum correntropy criterion (MCC) has recently been successfully applied in robust regression and filtering. The default kernel function in correntropy is the Gaussian kernel, which is, of course, not always the best choice. In this work, we propose a generalized correntropy that adopts the generalized Gaussian density (GGD) function as the kernel (not necessarily a Mercer kernel), and present some important properties. We further propose the generalized maximum correntropy criterion (GMCC), and apply it to adaptive filtering. An adaptive algorithm, called the GMCC algorithm, is derived, and the mean square convergence performance is studied. We show that the proposed algorithm is very stable and can achieve zero probability of divergence (POD). Simulation results confirm the theoretical expectations and demonstrate the desirable performance of the new algorithm.

stat.ML↗

arXiv2014

Salient Object Detection: A Discriminative Regional Feature Integration Approach

Salient object detection has been attracting a lot of interest, and recently various heuristic computational models have been designed. In this paper, we formulate saliency map computation as a regression problem. Our method, which is based on multi-level image segmentation, utilizes the supervised learning approach to map the regional feature vector to a saliency score. Saliency scores across multiple levels are finally fused to produce the saliency map. The contributions lie in two-fold. One is that we propose a discriminate regional feature integration approach for salient object detection. Compared with existing heuristic models, our proposed method is able to automatically integrate high-dimensional regional saliency features and choose discriminative ones. The other is that by investigating standard generic region properties as well as two widely studied concepts for salient object detection, i.e., regional contrast and backgroundness, our approach significantly outperforms state-of-the-art methods on six benchmark datasets. Meanwhile, we demonstrate that our method runs as fast as most existing algorithms.

cs.CV↗

arXiv2014

Kernel Least Mean Square with Adaptive Kernel Size

Kernel adaptive filters (KAF) are a class of powerful nonlinear filters developed in Reproducing Kernel Hilbert Space (RKHS). The Gaussian kernel is usually the default kernel in KAF algorithms, but selecting the proper kernel size (bandwidth) is still an open important issue especially for learning with small sample sizes. In previous research, the kernel size was set manually or estimated in advance by Silvermans rule based on the sample distribution. This study aims to develop an online technique for optimizing the kernel size of the kernel least mean square (KLMS) algorithm. A sequential optimization strategy is proposed, and a new algorithm is developed, in which the filter weights and the kernel size are both sequentially updated by stochastic gradient algorithms that minimize the mean square error (MSE). Theoretical results on convergence are also presented. The excellent performance of the new algorithm is confirmed by simulations on static function estimation and short term chaotic time series prediction.

stat.ML↗

arXiv2014

An Extended Result on the Optimal Estimation under Minimum Error Entropy Criterion

The minimum error entropy (MEE) criterion has been successfully used in fields such as parameter estimation, system identification and the supervised machine learning. There is in general no explicit expression for the optimal MEE estimate unless some constraints on the conditional distribution are imposed. A recent paper has proved that if the conditional density is conditionally symmetric and unimodal (CSUM), then the optimal MEE estimate (with Shannon entropy) equals the conditional median. In this study, we extend this result to the generalized MEE estimation where the optimality criterion is the Renyi entropy or equivalently, the α-order information potential (IP).

cs.IT↗