检索结果-内蒙古大学图书馆

Feasible Memory Access Prediction Using Short-Term, Online Machine Learning and Dynamic Vocabularies

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Sanchez-Cuevas, Pablo Diaz-Del-Rio, Fernando Casanueva-Morato, Daniel Rios-Navarro, Antonio Robotics and Technology of Computers Lab Universidad de Sevilla Spain

In recent years massive data computation has been intensified in order to meet the growing demand for all kinds of general and specific purpose *** the various approaches proposed in the field of Computer Architecture, a crucial bottleneck still remains: the efficiency and speed of memory *** bottleneck is trying to be overcome by prefetching, which is based on predicting the next memory address to be *** this paper, we initially study the most investigated techniques for address prediction and analyze the memory access pattern of popular software *** on this, we outline the main features of an efficient address predictor, and then we propose a new predictor that overcomes the detected drawbacks of other predictors: the SVM4AP (Support Vector Machine For Address Prediction). Comparisons have been carried out with maybe the most relevant predictor from the literature (DFCM);demonstrating that our SVM4AP achieves better cost-effectiveness than the DFCM in a range of different configurations. A notable difference is found for small-size predictors, where our proposal significantly surpasses DFCM and, thus, demonstrates its suitability for memory-constrained ***, an open-source tool is released that allows the scientific community to reproduce the results shown in this paper. © 2023, The Authors. All rights reserved.

关键词： Support vector machines

On Implementing the Sparse Events Closed-Loop Control Theory for the CartPoleSimulation 16th

学校读者我要写书评

暂无评论

On Implementing the Sparse Events Closed-Loop Control Theor...

16th EAI International Conference on Simulation Tools and Techniques, SIMUTools 2024

作者： Díaz-Romero, Santiago Paluch, Marcin Linares-Barranco, Alejandro Rios-Navarro, Antonio Robotics and Technology of Computers Lab. ETSII-EPS I3US SCORE Universidad de Sevilla Seville Spain Institute of NeuroInformatics UZH-ETHZ Zurich Switzerland

ISBN: (纸本)9783031873447

Event-based or neuro-inspired motor control systems communicate information through pulses, instantaneous bursts of electrical current that encode information very efficiently, as occurs in biological organisms. This work proposes a software implementation for sparse events closed-loop neuromorphic motor control theory (SECLOC) in a software tool. The control algorithm has been included in a simulator developed in Python, and publicly available, of a robotic cart controlling an inverted pendulum. The proposed implementations can be easily ported to any FPGA or microcontroller-based board and allow control of the real robotic cart. We have tested and verified the functionality using the algorithm to generate control events for proportional-integral-derivative (PID) and linear-quadratic-regulator (LQR) controllers and obtained the parameters equivalent to the proportionality, integrative, and derivative constants for these pulsing controllers. The empirical results demonstrate the validity of both the theory in simulation and its test in an actual robot in the pulsed domain. In the simulation, for angle control using a PID, with a minimum reaction time of 1 ms from the controller, the pendulum remains in equilibrium along the cart pole travel for more than 5 min, registering the 0-degree passage more than 2800 times. For the real pendulum used, the LQR controller, and the optimal control constants, with a minimum reaction time of 6 ms of the controller, the pendulum remains in equilibrium along the carriage path, as well as under slight and moderate perturbations without dropping during all experiments performed over a simulated period of almost 3.5 days. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2025.

关键词： Two term control systems

Integrating a hippocampus memory model into a neuromorphic robotic-arm for trajectory navigation

学校读者我要写书评

暂无评论

Integrating a hippocampus memory model into a neuromorphic r...

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Daniel Casanueva-Morato Pablo Lopez-Osorio Enrique Piñero-Fuentes Juan P. Dominguez-Morales Fernando Perez-Peña Alejandro Linares-Barranco Robotics and Technology of Computers Lab. SCORE Lab Universidad de Sevilla Sevilla Spain School of Engineering Universidad de Cádiz Spain

ISBN: (数字)9798350330991

ISBN: (纸本)9798350331004

Neuromorphic engineering endeavors to integrate the computational prowess and efficiency inherent in biological neuronal systems, such as the brain, into contemporary technological systems, primarily through the deployment of spiking neural networks. This research delineates the development and implementation of a bio-inspired sequential hippocampus memory model, which can effectively learn and sequentially recall memories, within a robotic infrastructure. The hippocampus memory model, implemented on the SpiNNaker platform, has been tactically utilized to control a 4-joint event-based robot arm, the ED-ScorBot, by learning and then recalling trajectories via a sequence of memories regarding joint positions. The conveyed spiking information from SpiNNaker is interpreted by an FPGA in real-time to command the event-driven motors of the robotic arm, integrating learned trajectories into physical robotic movement. An empirical exploration validates the model’s capability to govern the robotic arm’s trajectory with precision and dependability while simultaneously demonstrating the potential for incorporating spike-based memory models in robotic applications. This synergistic convergence of neuromorphic engineering and robotics illustrates a viable pathway towards sophisticated, efficient, and adaptable robotic systems capable of learning and reproducing complex tasks, with significant implications for future developments in autonomous robotic applications.

关键词： Adaptation models Service robots Neuromorphic engineering Navigation Arms Manipulators Brain modeling

A bio-inspired implementation of a sparse-learning spike-based hippocampus memory model

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Casanueva-Morato, Daniel Ayuso-Martinez, Alvaro Dominguez-Morales, Juan P. Jimenez-Fernandez, Angel Jimenez-Moreno, Gabriel The Robotics and Technology of Computers Lab Universidad de Sevilla Spain

The nervous system, more specifically, the brain, is capable of solving complex problems simply and efficiently, far surpassing modern computers. In this regard, neuromorphic engineering is a research field that focuses on mimicking the basic principles that govern the brain in order to develop systems that achieve such computational capabilities. Within this field, bio-inspired learning and memory systems are still a challenge to be solved, and this is where the hippocampus is involved. It is the region of the brain that acts as a short-term memory, allowing the learning and unstructured and rapid storage of information from all the sensory nuclei of the cerebral cortex and its subsequent recall. In this work, we propose a novel bio-inspired memory model based on the hippocampus with the ability to learn memories, recall them from a cue (a part of the memory associated with the rest of the content) and even forget memories when trying to learn others with the same cue. This model has been implemented on the SpiNNaker hardware platform using Spiking Neural Networks, and a set of experiments and tests were performed to demonstrate its correct and expected operation. The proposed spike-based memory model generates spikes only when it receives an input, being energy efficient, and it needs 7 timesteps for the learning step and 6 timesteps for recalling a previously-stored memory. This work presents the first hardware implementation of a fully functional bio-inspired spike-based hippocampus memory model, paving the road for the development of future more complex neuromorphic systems. © 2022, CC BY-NC-SA.

关键词： Brain

Spike-based building blocks for performing logic operations using Spiking Neural Networks on SpiNNaker

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ayuso-Martinez, Alvaro Casanueva-Morato, Daniel Dominguez-Morales, Juan P. Jimenez-Fernandez, Angel Jimenez-Moreno, Gabriel Robotics and Technology of Computers Lab Universidad de Sevilla Sevilla Spain

One of the most interesting and still growing scientific fields is neuromorphic engineering, which is focused on studying and designing hardware and software with the purpose of mimicking the basic principles of biological nervous systems. Currently, there are many research groups developing practical applications based on neuroscientific knowledge. This work provides researchers with a novel toolkit of building blocks based on Spiking Neural Networks that emulate the behavior of different logic gates. These could be very useful in many spike-based applications, since logic gates are the basis of digital circuits. The designs and models proposed are presented and implemented on a SpiNNaker hardware platform. Different experiments were performed in order to validate the expected behavior, and the obtained results are discussed. The functionality of traditional logic gates and the proposed blocks is studied, and the feasibility of the presented approach is discussed. © 2022, CC BY-NC-SA.

关键词： Logic gates

Spike-based computational models of bio-inspired memories in the hippocampal CA3 region on SpiNNaker

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Casanueva-Morato, Daniel Ayuso-Martinez, Alvaro Dominguez-Morales, Juan P. Jimenez-Fernandez, Angel Jimenez-Moreno, Gabriel Robotics and Technology of Computers Lab Universidad de Sevilla Sevilla Spain

The human brain is the most powerful and efficient machine in existence today, surpassing in many ways the capabilities of modern computers. Currently, lines of research in neuromorphic engineering are trying to develop hardware that mimics the functioning of the brain to acquire these superior capabilities. One of the areas still under development is the design of bio-inspired memories, where the hippocampus plays an important role. This region of the brain acts as a short-term memory with the ability to store associations of information from different sensory streams in the brain and recall them later. This is possible thanks to the recurrent collateral network architecture that constitutes CA3, the main sub-region of the hippocampus. In this work, we developed two spike-based computational models of fully functional hippocampal bio-inspired memories for the storage and recall of complex patterns implemented with spiking neural networks on the SpiNNaker hardware platform. These models present different levels of biological abstraction, with the first model having a constant oscillatory activity closer to the biological model, and the second one having an energy-efficient regulated activity, which, although it is still bio-inspired, opts for a more functional approach. Different experiments were performed for each of the models, in order to test their learning/recalling capabilities. A comprehensive comparison between the functionality and the biological plausibility of the presented models was carried out, showing their strengths and weaknesses. The two models, which are publicly available for researchers, could pave the way for future spike-based implementations and applications. © 2022, CC BY-NC-SA.

关键词： Brain

A Hybrid Neuromorphic Robotic-Arm Lemniscate Trajectories Dataset for Learning-Based Applications

学校读者我要写书评

暂无评论

A Hybrid Neuromorphic Robotic-Arm Lemniscate Trajectories Da...

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： E. Piñero-Fuentes D.A. Curra-Sosa D. Cascado S. Canas A. Rios-Navarro F. Gomez-Rodriguez A. Jimenez-Fernandez A. Linares-Barranco Robotics and Technology of Computers Lab. ETSH-EPS. I3US. SCORE. Universidad de Sevilla Seville Spain

ISBN: (数字)9798350377200

ISBN: (纸本)9798350377217

In this work, an all-in-one neuromorphic motors controller system with reduced latency and power consumption for a robotic arm is used to record a dataset of trajectories for learning applications. Unlike human-created encoding systems, biological neural ones use neurons and spikes to process the information and make weighted decisions based on a continuous learning process. A central pattern generator is a biological structure that orchestrates the activity of motor neurons, causing muscle fibers to elongate and contract through signals generated by spikes. This process allows for the replication of learned movement patterns or trajectories. The Event-Driven Scorbot platform (ED-Scorbot) consists of a six Degrees of Freedom (DoF) robotic arm, whose controller implements a Spiking Proportional-Integrative-Derivative (SPID) algorithm, mimicking biological systems. In this paper, the ED-Scorbot is used to record a series of lemniscate trajectories drawn by the end-effector in the Cartesian space. These trajectories have been produced with different heights, widths, foci distances and orientation angles within the robot's working area. Different weights at the end-effector are used to enrich the dataset. MP4 videos, internal spiking activity, joint sensors output and target trajectory are included in this hybrid dataset. For its validation, the spiking activity has been used to train and test a recurrent Spiking Neural Networks (SNN) to classify the weight attached to the gripper with an accuracy of 83.3% on test samples.

关键词： Neuromorphics Neurons Kinematics Robot sensing systems Motors Control systems End effectors Trajectory Biological information theory Videos

An MPSoC-based on-line Edge Infrastructure for Embedded Neuromorphic Robotic Controllers

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Pinero-Fuentes, Enrique Canas-Moreno, Salvador Rios-Navarro, Antonio Cascado-Caballero, Daniel Jimenez-Fernandez, Angel Linares-Barranco, Alejandro Robotics and Technology of Computers Lab. I3US SCORE University of Seville Seville Spain

In this work, an all-in-one neuromorphic controller system with reduced latency and power consumption for a robotic arm is presented. Biological muscle movement consists of stretching and shrinking fibres via spike-commanded signals that come from motor neurons, which in turn are connected to a central pattern generator neural structure. In addition, biological systems are able to respond to diverse stimuli rather fast and efficiently, and this is based on the way information is coded within neural processes. As opposed to human-created encoding systems, neural ones use neurons and spikes to process the information and make weighted decisions based on a continuous learning process. The Event-Driven Scorbot platform (ED-Scorbot) consists of a 6 Degrees of Freedom (DoF) robotic arm whose controller implements a Spiking Proportional-Integrative-Derivative algorithm, mimicking in this way the previously commented biological systems. In this paper, we present an infrastructure upgrade to the ED-Scorbot platform, replacing the controller’s hardware, which was comprised of two Spartan Field Programmable Gate Arrays (FPGAs) and a barebone computer, with an edge device, the Xilinx Zynq-7000 SoC (System on Chip) which reduces the response time, power consumption and overall complexity. © 2022, CC BY.

关键词： Python

Towards spiking analog hardware implementation of a trajectory interpolation mechanism for smooth closed-loop control of a spiking robot arm

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Casanueva-Morato, Daniel Wu, Chenxi Indiveri, Giacomo Dominguez-Morales, Juan P. Linares-Barranco, Alejandro Robotics and Technology of Computers Lab. ETSII-EPS Universidad de Sevilla Sevilla Spain I3US Universidad de Sevilla Spain SynSense AG Corporation Zurich Switzerland Institute of Neuroinformatics University of Zurich and ETH Zurich Switzerland

Neuromorphic engineering aims to incorporate the computational principles found in animal brains, into modern technological systems. Following this approach, in this work we propose a closed-loop neuromorphic control system for an event-based robotic arm. The proposed system consists of a shifted Winner-Take-All spiking network for interpolating a reference trajectory and a spiking comparator network responsible for controlling the flow continuity of the trajectory, which is fed back to the actual position of the robot. The comparator model is based on a differential position comparison neural network, which governs the execution of the next trajectory points to close the control loop between both components of the system. To evaluate the system, we implemented and deployed the model on a mixed-signal analog-digital neuromorphic platform, the DYNAPSE2, to facilitate integration and communication with the ED-Scorbot robotic arm platform. Experimental results on one joint of the robot validate the use of this architecture and pave the way for future neuro-inspired control of the entire robot. © 2025, CC BY-NC-SA.

关键词： Comparators (optical)