BPS: a learning algorithm for capturing the dynamic nature of speech

This paper is concerned with stability analysis for a class of dynamical neural networks with distributed delays. The M-matrix theory and new analysis technique are used to obtain new sufficient conditions for the existence, uniqueness and global stability of the equilibrium point of dynamical neural networks with distributed delays. The importance of the new stability criteria in the design and application of dynamical neural networks with distributed delays is due to the fact that they can handle the case when the non-delayed terms can not dominate the delayed terms. The effectiveness of the obtained theoretical results are illustrated by numerical examples.

Fundamental to a systematic synthesis of neural networks for optimization, associative memory and continuous mapping applications is a qualitative analysis of the network equilibrium conditions and the convergence of network trajectories to these equilibria. Specific conditions using the theory of P-matrices are developed in this paper for characterizing the equilibrium conditions and the stability properties for an important class of neural networks that has received wide attention. Network structures for ensuring equilibrium confinement are identified by determining conditions for uniqueness of stable equilibrium points in specified quadrants of the state space. Conditions on network parameters for ensuring exponential stability with an arbitrarily specified degree within the basins of attraction of the equilibrium points are also presented. These results serve as valuable guidelines in the synthesis of neural networks for any specific application.

The running time and memory requirement of a parallel program with dynamic, lightweight threads depends heavily on the underlying thread scheduler. In this paper we present a new asynchronous, space-efficient scheduling algorithm for shared memory machines that combines the low scheduling overheads and good locality of work stealing with the low space requirements of depth-first schedulers. For a nested-parallel program with depth D and serial space requirement S 1 , we show that the expected space requirement is S 1 + O(K⋅ p⋅ D) on p processors. Here, K is a user-adjustable runtime parameter, which provides a tradeoff between running time and space requirement. Our algorithm achieves good locality and low scheduling overheads by automatically increasing the granularity of the work scheduled on each processor. We have implemented the new scheduling algorithm in the context of a native, user-level implementation of Posix standard threads or Pthreads, and evaluated its performance using a set of C-based benchmarks that have dynamic or irregular parallelism. We compare the performance of our scheduler with that of two previous schedulers: the thread library's original scheduler (which uses a FIFO queue), and a provably space-efficient depth-first scheduler. At a fine thread granularity, our scheduler outperforms both these previous schedulers, but requires marginally more memory than the depth-first scheduler. We also present simulation results on synthetic benchmarks to compare our scheduler with space-efficient versions of both a work-stealing scheduler and a depth-first scheduler. The results indicate that unlike these previous approaches, the new algorithm covers a range of scheduling granularities and space requirements, and allows the user to trade the space requirement of a program with the scheduling granularity.

Buffer insertion and wire sizing are critical in deep submicron VLSI design. This paper studies the problem of constructing routing trees with simultaneous buffer insertion and wire sizing in the presence of routing and buffer obstacles. No previous algorithms consider all these factors simultaneously. Previous dynamic programming based algorithm is first extended to solve the problem. However, with the size of routing graph increasing and with wire sizing taken into account, the time and space requirement increases enormously. Then a new approach is proposed to formulate the problem as a series of graph problems. The routing tree solution is obtained by finding shortest paths in a series of graphs. In the new approach, wire sizing can be handled almost without any additional time and space requirement, Moreover, the time and space requirement is only polynomial in terms of the size of routing graph. Our algorithm differs from traditional dynamic programming, and is capable of addressing the problem of inverter insertion and sink polarity. Both theoretical and experimental results show that the graph-based algorithm outperforms the DP-based algorithm by a large margin. We also propose a hierarchical approach to construct routing tree for a large number of sinks.

An increasing number of applications of dynamic neural networks has been developed for digital signal processing (DSP), dynamic neural networks are feedforward neural networks with commonly used scalar synapses replaced by linear filters. This provides feedforward neural networks with the capability of performing dynamic mappings, which depend on past input values, dynamic neural networks are suitable for time series prediction, nonlinear system identification, and signal processing applications. Their most popular types are Finite Impulse Response (FIR) neural networks, which are obtained by replacing synapses with finite impulse response filters. Due to their guaranteed stability characteristic and easy to minimize error surface they have been used with great success in many applications such as signal enhancement, noise cancellation, classification of input patterns, system identification, prediction, and control.. Most of the works on system identification using neural networks are based on multilayer feedforward neural networks with backpropagation learning or more efficient variations of this algorithm, an elegant method for training layered networks. This paper is based on work in a Dynamic System Modeling (DYSMO) and as an application for speed control of DC motor drive.

Data stream is a new data model that has recently attracted attentions in numerous applications. Considering the continuity, limitlessness of streaming data, this paper proposes a novel method to build a synopsis data structure, Nord_Histogram, for storing streaming data summary and a one-pass approximate algorithm, NHQC, for quantile computation. The algorithm implements quantile queries over data stream with the time and space requirements being linear with the number of buckets, beating several previous synopsis structure and algorithms in terms of time and space costs which grow at least logarithmically with the length of data stream. The correlation between computation error and main memory requirement is also analyzed. Experiment results show the good performance of NHQC with desirable accuracy and efficient time and space requirements.

Recurrent neural networks unlike feed-forward networks are able to process inputs with time context. The key role in this process is played by the dynamics of the network, which transforms input data to the recurrent layer states. Several authors have described and analyzed dynamics of small sized recurrent neural networks with two or three hidden units. In our work we introduce techniques that allow to visualize and analyze the dynamics of large recurrent neural networks with dozens units, reveal both stable and unstable points (attractors and saddle points), which are important to understand the principles of successful task processing. As a practical example of this approach, dynamics of the simple recurrent network trained by two different training algorithms on context-free language anbnwas studied.

With the advent of mobile robots in commercial applications, the problem of path-planning has acquired significant attention from the research community. An optimal path for a mobile robot is measured by various factors such as path length, collision-free space, execution time, and the total number of turns. MEA* is an efficient variation of A* for optimal path-planning of mobile robots. RRT*-AB is a sampling-based planner with rapid convergence rate, and improved time and space requirements than other sampling-based methods such as RRT*. The purpose of this paper is the review and performance comparison of these planners based on metrics, i.e., path length, execution time, and memory requirements. All planners are tested in structured and complex unstructured environments cluttered with obstacles. Performance plots and statistical analysis have shown that MEA* requires less memory and computational time than other planners. These advantages of MEA* make it suitable for off-line applications using small robots with constrained power and memory resources. Moreover, performance plots of path length of MEA* is comparable to RRT*-AB with less execution time in the 2D environment. However, RRT*-AB will outperform MEA* in high-dimensional problems because of its inherited suitability for complex problems.

In this paper, we present a timed automaton reachability analysis algorithm which can use some other properties to improve the model checking efficiency. If the model checker aborts because of memory or CPU time limitation when checking a property P, the users can still use a set of auxiliary properties P <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> , P <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ,..., P <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</sub> about the system to reduce the space and time requirement. People can verify these auxiliary properties by either model checking or other methods like theorem proving. This algorithm gives the users a way to reduce the space and time requirement of model checking using their knowledge about the system under check.

Temporal Graph Clustering (TGC) is a new task with little attention, focusing on node clustering in temporal graphs. Compared with existing static graph clustering, it can find the balance between time requirement and space requirement (Time-Space Balance) through the interaction sequence-based batch-processing pattern. However, there are two major challenges that hinder the development of TGC, i.e., inapplicable clustering techniques and inapplicable datasets. To address these challenges, we propose a comprehensive benchmark, called BenchTGC. Specially, we design a BenchTGC Framework to illustrate the paradigm of temporal graph clustering and improve existing clustering techniques to fit temporal graphs. In addition, we also discuss problems with public temporal graph datasets and develop multiple datasets suitable for TGC task, called BenchTGC Datasets. According to extensive experiments, we not only verify the advantages of BenchTGC, but also demonstrate the necessity and importance of TGC task. We wish to point out that the dynamically changing and complex scenarios in real world are the foundation of temporal graph clustering.

Can we solve finite-horizon Markov decision processes (FHMDPs) while raising low memory requirements? Such models find application in many cases where a decision-making agent needs to act in a probabilistic environment, from resource management to medicine to service provisioning. However, computing optimal policies such an agent should follow by dynamic programming value iteration raises either prohibitive space complexity, or, in reverse, non-scalable time complexity requirements. This scalability question has been largely neglected. In this paper, we propose SIFTER (Space Efficient Finite Horizon MDPs), a suite of algorithms that achieve a golden middle between space and time requirements. Our former algorithm raises space complexity growing with the square root of the horizon's length without a time-complexity overhead, while the latter's space requirements depend only logarithmically in horizon length with a corresponding logarithmic time complexity overhead. A thorough experimental study under diverse settings confirms that SIFTER algorithms achieve the predicted gains, while approximation techniques do not achieve the same combination of time efficiency, space efficiency, and result quality.

Robotic aid in minimally invasive surgery (MIS) is becoming more and more common. We designed an experimental trial in a phantom model to verify the feasibility of solo surgery for MIS. By performing laparoscopic cholecystectomy on a phantom model, we compared combinations of different systems available in terms of safety, comfort, and time requirements. Two surgeons skilled in endoscopic procedures tested the following systems as endoscope holders: the robotic system (AESOP), foot-controlled (AESOP 1000), and voice-controlled (AESOP 2000); the remote controlled FIPS Endoarm, electrically driven and controlled by a finger-ring joystic; the passive system TISKA Endoarm, a mechanical arm moved by hand and fixed by electromagnetical brakes. All of these systems combined with a second TISKA Endoarm as an instrument holder. A combination of two mechanical Martin arms, c, also was tested. The results were compared with those from a control group involving an assistant surgeon. A total of 70 experiments were performed. The shortest dissection time was registered by the combination of two TISKA Endoarms, with a statistically significant difference as compared with the control group (p < 0.05) and experiments using AESOP 1000 (p < 0.05). The TISKA Endoarm also proved to be more comfortable when used as an instrument holder (p < 0.001 vs Martin arm), and rated second only to AESOP 2000 as an endoscope holder. The rating of AESOP 2000 as endoscope holder was significantly higher than that of all other groups (p < 0.001). The study proved the feasibility of solo surgery. The time needed for dissection was shortest when two TISKA Endoarms were used, demonstrating the possible advantages of solo surgery. The TISKA Endoarm received a subjective positive rating when used as both endoscope holder and instrument holder. The voice control of AESOP 2000 seemed to be a major improvement in the development of an optimal man-machine interface. Nevertheless, the system presents considerable space requirements and does not supply control of 30 degrees optics. The principle of the finger-ring joystick adopted by the FIPS Endoarm seemed very intuitive but lacking in ergonomy. Laparoscopic solo surgery can be considered a safe procedure, although further technologic developments should lead to improved ergonomy, intuitiveness of handling, and architecture of the systems, offering the surgeon better control, increased precision of action, and reduction in operation time.

With the ubiquity of complex networks in domains as diverse as social network analysis, recommender systems and epidemiology, improvements in link predictions have a potential for far-reaching impact. In machine learning, a well-known approach to improve classification performance is to combine several methods in an ensemble. It is also well established that, diversity or complementarity of the classifiers to be combined, is a prerequisite for a potential performance improvement of the formed ensemble. In this work, we combine link prediction heuristics (e.g. Common Neighbour, Adamic-Adar etc.), with static graph neural networks, discrete dynamic graph neural networks, and continuous dynamic graph neural networks. We analyze the importance of each of the methods and how complementary they are with respect to each other. We also use greedy searches to select better subsets of methods to combine and train the ensemble in a roll-forward manner to make it adapt to changes in the dynamic network over time. In the conducted experiments on a number of challenging link prediction tasks, the ensemble from the greedy search and the roll-forward ensemble shows on average a 55% and 61% improvement respectively, over the best single method.

With the rapid advancement of high-speed railways worldwide, the demands of track construction tasks have grown increasingly complex and stringent. Many construction activities rely heavily on train operations, introducing significant challenges to train scheduling. Conflicts frequently arise among train tasks due to overlapping requirements in time, space, and resource allocation. Traditional manual scheduling approaches often fall short in addressing the complexities of these scenarios, underscoring the necessity for intelligent optimization methods. This study presents an optimized scheduling approach tailored specifically to train tasks in high-speed railway construction scenarios. A multi-objective optimization model is proposed, incorporating factors such as task priority, time window constraints, and track resource utilization. The primary objectives are to minimize task completion time, enhance resource efficiency, and ensure operational safety. Additionally, the scheduling of entry, exit, and waiting lines is examined to address practical operational needs. To further improve efficiency, a dynamic waiting line mechanism is designed to facilitate train avoidance and prioritize passage. Solutions to the proposed model are obtained using the Gurobi solver. The applicability and effectiveness of the scheduling scheme are validated through on-site data testing. Results demonstrate that the proposed method significantly improves construction efficiency, reduces resource waste, and enhances overall operational reliability. This research provides theoretical insights and practical methodologies for intelligent scheduling management in high-speed railway construction, contributing to the efficient, green, and sustainable development of rail transit systems in China.

Introduction: The Timed Up and Go (TUG) is a simple, quick and easy-to-use test to detect general functional mobility performance in many populations including COPD. Although the 6-minute walk test (6MWT) is commonly used to evaluate functional capacity in persons with pulmonary arterial hypertension (PAH), it can be difficult to use since its requirements of time and open space. Additionally, the length of test limits its use in more disabled patients. Aims: To investigate the associations between the TUG and other mobility and disease related variables. Methods: Twenty-three patients with PAH were included in this cross-sectional study. Functional status was determined by the 6MWT. Peripheral muscle strength was measured with a hand-held and hand-grip dynamometer. Respiratory muscle strength was measured with a digital pressure manometer. Disease severity was determined by the New York Heart Association functional classification. Physical activity was also measured with the International Physical Activity Questionnaire. Results: There was a significant strong correlation between the TUG and 6MWT, hand-grip strength, respiratory muscle strength, and physical activity (p Conclusion: This study suggests that the TUG can be considered as a potential objective test to evaluate patients with PAH, since it was strongly associated with other mobility and disease related variables.