The frequency and the extent of damages caused by network attacks have been actually increasing greatly in recent years, although many approaches to avoiding and detecting attacks have been proposed in the community o...
详细信息
ISBN:
(纸本)9781479957330
The frequency and the extent of damages caused by network attacks have been actually increasing greatly in recent years, although many approaches to avoiding and detecting attacks have been proposed in the community of network security. Thus, how to fast detect actual or potential attacks has become an urgent issue. Among the detection strategies, behavior-based ones, which use normal access patterns learned from reference data (e.g., history traffic) to detect new attacks, have attracted attention from many researchers. In each of all such strategies, a learning algorithm is necessary and plays a key role. Obviously, whether the learning algorithm can extract the normal behavior modes properly or not directly influence the detection result. However, some parameters have to determine in advance in the existing learning algorithms, which is not easy, even not feasible, in many actual applications. For example, even in the newest learning algorithm, which called FHST learning algorithm in this study, two parameters are used and they are difficult to be determined in advance. In this study, we propose a parameterless learning algorithm for the first time, in which no parameters are used. The efficiency of our proposal is verified by experiment. Although the proposed learning algorithm in this study is designed for detecting port scans, it is obviously able to be used to other behavior-based detections.
Aimed at the problem of deviation of uncertainty estimates in the test model of attributes selecting with the information gain, an improved learning algorithm of decision tree based on the uncertainty deviation of ent...
详细信息
ISBN:
(纸本)9781467321013;9781467321006
Aimed at the problem of deviation of uncertainty estimates in the test model of attributes selecting with the information gain, an improved learning algorithm of decision tree based on the uncertainty deviation of entropy measure was developed. In the algorithm, the method of regulating oppositely deviation of the information entropy peak through a sine function was used, when test of attributes choice with information gain the adverse effect of deviation of information entropy peak was restrained. Compared with the ID3, the improvement of classification performance was acquired while its better stability of performance for its decision tree. The research results show that the rationality of attribute selection test was effectively improved through the method based on the entropy uncertainty deviation.
Using gradient descent, we propose a new backpropagation learning algorithm for spiking neural networks with multi-layers, multi-synapses between neurons, and multi-spiking neurons. It adjusts synaptic weights, delays...
详细信息
ISBN:
(纸本)9783319466729;9783319466712
Using gradient descent, we propose a new backpropagation learning algorithm for spiking neural networks with multi-layers, multi-synapses between neurons, and multi-spiking neurons. It adjusts synaptic weights, delays, and time constants, and neurons' thresholds in output and hidden layers. It guarantees convergence to minimum error point, and unlike SpikeProp and its extensions, does not need a one-to-one correspondence between actual and desired spikes in advance. So, it is stably and widely applicable to practical problems.
Metasearching is the process of combining search results of different search systems into a single set of ranked results, which is expected to be better than results of best of the participating search systems. In thi...
详细信息
ISBN:
(纸本)9781424415502
Metasearching is the process of combining search results of different search systems into a single set of ranked results, which is expected to be better than results of best of the participating search systems. In this paper, we present a supervised learning algorithm for metasearching. Our algorithm learns the ranking rules on the basis of user feedback based metasearching for the queries in the training set. We use rough set theory to mine the ranking rules. The ranking rules are validated using cross validation. The best of the ranking rules is then used to estimate the results of metasearching for the other queries. We compare our method with modified Shimura technique. We claim that our method is more useful than modified Shimura technique as it models user's preference.
This paper shows a tenacity learning algorithm that prioritizes static over dynamic stability to decrease gait complexity for an articulated humanoid robot. Initially, we have an array of goal positions, which the alg...
详细信息
ISBN:
(纸本)9781728156354
This paper shows a tenacity learning algorithm that prioritizes static over dynamic stability to decrease gait complexity for an articulated humanoid robot. Initially, we have an array of goal positions, which the algorithm must achieve during the gait cycle. A trial and error process leads the learning approach. Each robot motion attempt is available on an action list. Whenever the robot achieves a goal, the algorithm stores the sequence of movements in memory. If there is a failure, the action list provides the position before the fall - and the process starts from that point on. In order to test the algorithm, we developed a simulator using Matlab Simulink, together with the Simscape Multibody contact forces library. We present the simulation data through graphs that describe the behavior of the joints during the learning process of a gait cycle.
A generalization from string to trees and from languages to translations is given of the classical result that any regular language can be learned from examples: it is shown that for any deterministic top-down tree tr...
详细信息
ISBN:
(纸本)9781450300339
A generalization from string to trees and from languages to translations is given of the classical result that any regular language can be learned from examples: it is shown that for any deterministic top-down tree transformation there exists a sample set of polynomial size (with respect to the minimal transducer) which allows to infer the translation. Until now, only for string transducers and for simple relabeling tree transducers, similar results had been known. learning of deterministic top-down tree transducers (DTOPs) is far more involved because a DTOP can copy, delete, and permute its input subtrees. Thus, complex dependencies of labeled input to out put paths need to be maintained by the algorithm. First, a Myhill-Nerode theorem is presented for DTOPs, which is interesting on its own. This theorem is then used to construct a learning algorithm for DTOPs. Finally, it is shown how our result can be applied to XML transformations (e.g. XSLT programs). For this, a new DTD-based encoding of unranked trees by ranked ones is presented. Over such encodings, DTOPs can realize many practically interesting XML transformations which cannot be realized on first-child/next-sibling encodings.
This paper devoted for the implementation of a learning algorithm, utilized Artificial Neural Network (ANN), to predict the passive joint angular positioning for 3R under-actuated serial robot. Under-actuated system h...
详细信息
This paper devoted for the implementation of a learning algorithm, utilized Artificial Neural Network (ANN), to predict the passive joint angular positioning for 3R under-actuated serial robot. Under-actuated system has less number of actuators than the degrees of freedom; therefore, the estimating or modelling of its behaviour is difficult with many uncertainties. Thus, to overcome the disadvantages of several methods reported in literatures. A specific ANN model has been designed and trained to learn a desired set of joint angular positions for the passive joint from a given set of input torques and angular positions for the active joints over a certain period of time. ANN proposes from being free model technique. Consequently, data from sensors fixed on each joints were collected experimentally and provided for the developed ANN model. The learning algorithm can directly determine the position of its passive joint, and can, therefore, completely eliminate the need for any system modelling. Hence, this method could be generalized for the prediction of under-actuated systems behaviour. Results show a successful implementation of the learning algorithm in predicting the behaviour for 3R underactuated robot.
The unit feedback recursive neural network model which is widely used at present has been analyzed. It makes the unit feedback recursive neural network have the same dynamic process and time delay characteristic. The ...
详细信息
ISBN:
(数字)9783642330308
ISBN:
(纸本)9783642330292;9783642330308
The unit feedback recursive neural network model which is widely used at present has been analyzed. It makes the unit feedback recursive neural network have the same dynamic process and time delay characteristic. The applications of the unit recursive neural networks are limited. For its shortcomings, we proposed another state feedback recursive neuron model, and their state feedback recursive neural network model. In this neural network model, the static weight of the neural network explained the static transmission performance, and the state feedback recursive factor indicated the dynamic performance of neural networks, the different state feedback recursion factor indicated the dynamic process time of the different systems.
The strategy using approximate/adaptive dynamic programming (ADP) has been widely used to design a learning controller for complex systems of higher dimension in recent years. This paper aims at handling an important ...
详细信息
ISBN:
(纸本)9783642384608;9783642384592
The strategy using approximate/adaptive dynamic programming (ADP) has been widely used to design a learning controller for complex systems of higher dimension in recent years. This paper aims at handling an important problem in the design of ADP learning controllers, which is the improvement of learning algorithm for its convergence performance. We analyze ADP controller implementation framework according to the requirement of tracking control task, with emphasis on providing an improved weight-updating gradient descent approach in optimizing connection weights in network structures. A comparison of the proposed method and classic ADP design for tracking and controlling pitch angle of aircraft is presented. It verifies the feasibility in the design of the proposed ADP based controller.
Cellular Automata was applied to model the pedestrian flow, where the local neighbor and transition rules implemented to each person in the crowd were determined automatically by the experience of pedestrians. The exp...
详细信息
ISBN:
(纸本)9783642159787
Cellular Automata was applied to model the pedestrian flow, where the local neighbor and transition rules implemented to each person in the crowd were determined automatically by the experience of pedestrians. The experience was based on two parameters;the number of continuous vacant cells in front of the cell to proceed, and the number of pedestrian in the cell to proceed. The experience was evaluated numerically, and a pedestrian selected the cell to proceed by the evaluated index. The flow formations by pedestrians in the opposite direction on a straight pathway and on a corner were simulated, and the number of rows was discussed in relation to the density of pedestrian on the simulation space.
暂无评论