Is it worth generating rules from neural network ensembles?

Although many authors generated comprehensible models from individual networks, much less work has been done in the explanation of ensembles. DIMLP is a special neural network model from which rules are generated at the level of a single network and also at the level of an ensemble of networks. We applied ensembles of 25 DIMLP networks to several datasets of the public domain and a classification problem related to post-translational modifications of proteins. For the classification problems of the public domain, the average predictive accuracy of rulesets extracted from ensembles of neural networks was significantly better than the average predictive accuracy of rulesets generated from ensembles of decision trees. By varying the architectures of DIMLP networks we found that the average predictive accuracy of rules, as well as their complexity were quite stable. The comparison to other rule extraction techniques applied to neural networks showed that rules generated from DIMLP ensembles gave very good results. In the last problem related to bioinformatics, the best result obtained by ensembles of DIMLP networks was also significantly better than the best result obtained by ensembles of decision trees. Thus, although neural networks take much longer to train than decision trees and also rules are generated at a greater computational cost (however, still polynomial), at least for several classification problems it was worth using neural network ensembles, as extracted rules were more accurate, on average. The DIMLP software is available for PC-Linux under http://us.expasy.org/people/Guido.Bologna.html.     

内隐记忆中通道效应的认知与神经机制

通道转换是使内隐和外显记忆任务之间产生功能性分离经常操纵的典型变量之一,被看作是内隐记忆主要依赖刺激知觉住处加工的有利语气。该文回顾了近些年通道效应实验和理论研究的有关文献。对产生通道效应的认知机制和神经解剖基础进行了总结和分析,并提出了有待于进一步验证的问题。     

Sober social networks: The role of online support groups in recovery from alcohol addiction

In the context of addiction research, positive recovery outcomes are affected by the quality of people's social interactions and perhaps to an even greater extent, by the defining norms of the groups they identify with—that is, using versus recovery groups. Here, we examine the role of online supportive networks in the process of recovery from alcohol addiction. We analyse the relationship between negative and positive aspects of recovery capital (i.e., self‐stigma, and respectively, positive recovery identity and self‐efficacy) as they relate to well‐being outcomes among alcohol users in an online recovery support group. Based on a computerised linguistic analysis of the naturally occurring data extracted from an online recovery support group (i.e., 257 posts made by 237 group members), we found that self‐stigma negatively predicts self‐efficacy and well‐being, and social identification with a recovery identity mediates these relationships. Overall, these findings highlight that positive engagement with supportive recovery networks is central to an effective and sustainable recovery.     

The unfolding argument: Why IIT and other causal structure theories cannot explain consciousness

How can we explain consciousness? This question has become a vibrant topic of neuroscience research in recent decades. A large body of empirical results has been accumulated, and many theories have been proposed. Certain theories suggest that consciousness should be explained in terms of brain functions, such as accessing information in a global workspace, applying higher order to lower order representations, or predictive coding. These functions could be realized by a variety of patterns of brain connectivity. Other theories, such as Information Integration Theory (IIT) and Recurrent Processing Theory (RPT), identify causal structure with consciousness. For example, according to these theories, feedforward systems are never conscious, and feedback systems always are. Here, using theorems from the theory of computation, we show that causal structure theories are either false or outside the realm of science.     

Social network members' responses to friends' breakup false alarms

Social networks influence romantic relationships through friends' support or lack of support of the union. However, the consequences of friends repeatedly telling other friends their relationship was going to end but failing to actually terminate the relationship are unclear. Guided by the false alarm effect (FAE), and data from both student (N = 273) and noncollege (N = 226) samples, it was found that breakup false alarms were associated with increases in both positive and negative responses. In addition, when participants were friends with both partners, breakup false alarms were associated with “feeling caught” between the friends. Findings generally support the FAE and paint a complex picture of how social network members react to their close friends' tumultuous relationships.     

An improved energy efficient cluster head selection protocol using the double cluster heads and data fusion methods for IoT applications

The more energy consumption is the major issue for wireless sensor network. In wireless sensor network (WSN), sensor nodes are fixed in various routing algorithms. In the same networks, mobile sensor and fixed sensor nodes are combine and its used in few applications. The function is corruption while mobility was achieved, since these nodes have minimum battery power, lower range of communication and a lessor amount of memory. To overcome this issue, Improved Energy Efficient Cluster Head Selection protocol (IEECHS-WSN) is proposed, in these technique is used to transfer the received information by using energy efficient routing protocol. In the CH election method, two cluster heads are selected in a separated cluster and its work in various functions, this can be prolong the network lifetime and decrease the energy consumption of IoT applications. Proposed technique is described on clustering of dual CHs in the method of data fusion for data entropy. This information entropy is used for fusion and classification, the result of fusion and classification are accurate and efficient for data transmission. Our proposed IEECHS protocol has better throughput, lifetime of network and energy consumption compared than the existing technique.     

An accurate and efficient multi-category edge detection method

Edge detection plays an important role in image processing. With the development of deep learning, the accuracy of edge detection has been greatly improved, and people have more requirements for edge detection tasks. Most edge detection algorithms are binary edge detection methods, but there are usually multiple categories of edges in an image. In this paper, we present an accurate multi-category edge detection network, the richer category-aware semantic edge detection network (R-CASENet). In order to make full use of convolutional neural network’s powerful feature expression capabilities, we attempt to use more information from feature maps for edge feature extraction and classification. Using the ResNet101 network as the backbone, firstly we merge the building blocks in different composite blocks and down-sample to obtain the feature maps. Then we fuse the feature maps in different composite blocks to obtain the final fused classifier. Experimental results show that R-CASENet can achieve state-of-the-art performance on the large SBD dataset. Furthermore, to get precise one-pixel width edges, we also propose an edge refinement network (ERN) structure. The proposed scheme is an end-to-end method and the proposed ERN can reduce redundant points and improve computational efficiency, especially for further image processing.     

Populations of spiking neurons for reservoir computing: Closed loop control of a compliant quadruped

Compliant robots can be more versatile than traditional robots, but their control is more complex. The dynamics of compliant bodies can however be turned into an advantage using the physical reservoir computing framework. By feeding sensor signals to the reservoir and extracting motor signals from the reservoir, closed loop robot control is possible. Here, we present a novel framework for implementing central pattern generators with spiking neural networks to obtain closed loop robot control. Using the FORCE learning paradigm, we train a reservoir of spiking neuron populations to act as a central pattern generator. We demonstrate the learning of predefined gait patterns, speed control and gait transition on a simulated model of a compliant quadrupedal robot.     

On simulating one-trial learning using morphological neural networks

“Learning once, remembering forever”, this wonderful cognitive phenomenon sometimes occurs in the learning process of human beings. Psychologists call this psychological phenomenon “one-trial learning”. The traditional artificial neural networks can simulate the psychological phenomenon of “implicit learning”, but can’t simulate the cognitive phenomenon of “one-trial learning”. Therefore, cognitive psychology gives a challenge to the traditional artificial neural networks. From two aspects of theory and practice in this paper, the possibility of simulating this kind of psychological phenomenon was explored by using morphological neural networks. This paper takes advantage of morphological associative memory networks to realize the simulation of “one-trial learning” for the first time, and gives 5 simulating practical examples. Theoretical analysis and simulation experiments show that the morphological associative memory networks are a higher effective machine learning method, and can better simulate the cognitive phenomenon of “one-trial learning”, therefore provide a theoretical basis and technological support for the study of intelligent science and cognitive science.     

赌博障碍的认知功能缺陷及神经基础

赌博障碍是指持续且反复的赌博行为,给个人、家庭和社会都带来了严重后果,近年来受到越来越多研究者的关注。本研究总结了赌博障碍的认知功能缺陷及其神经基础,主要集中在如下四个方面：①认知扭曲、②奖赏和惩罚敏感性、③注意偏向和④决策。未来研究应多从认知神经科学角度深入探究赌博障碍的发生机制和发展过程,关注大脑结构变化及功能网络改变,并将其整合到一个统一的神经生物机制框架中,找到更加有效的干预和治疗手段。