Spiking neural networks (SNNs) are bio-plausible computing models with high energy efficiency. The temporal dynamics of neurons and synapses enable them to detect temporal patterns and generate sequences. While Backpr...
Spiking neural networks (SNNs) are bio-plausible computing models with high energy efficiency. The temporal dynamics of neurons and synapses enable them to detect temporal patterns and generate sequences. While Backpropagation Through Time (BPTT) is traditionally used to train SNNs, it is not suitable for online learning of embedded applications due to its high computation and memory cost as well as extended latency. In this work, we present Spatiotemporal Online Learning for Synaptic Adaptation (SOLSA), which is specifically designed for online learning of SNNs composed of Leaky Integrate and Fire (LIF) neurons with exponentially decayed synapses and soft reset. The algorithm not only learns the synaptic weight but also adapts the temporal filters associated to the synapses. Compared to the BPTT algorithm, SOLSA has much lower memory requirement and achieves a more balanced temporal workload distribution. Moreover, SOLSA incorporates enhancement techniques such as scheduled weight update, early stop training and adaptive synapse filter, which speed up the convergence and enhance the learning performance. When compared to other non-BPTT based SNN learning, SOLSA demonstrates an average learning accuracy improvement of 14.2%. Furthermore, compared to BPTT, SOLSA achieves a 5% higher average learning accuracy with a 72% reduction in memory cost.
Capacitive sensing technology is widely applied in ubiquitous sensing. Its low-power consumption enables it to be used in a wide variety of Industry 4.0 applications. Capacitive Sensors can be combined into Arrays (CS...
Capacitive sensing technology is widely applied in ubiquitous sensing. Its low-power consumption enables it to be used in a wide variety of Industry 4.0 applications. Capacitive Sensors can be combined into Arrays (CSAs) with mutual capacitive sensing to reduce external wiring requirements. For instance, the Texas Instruments (TI) MSP430FR2676 can capture and process data from 8×8 capacitive sensor grids. However, it is limited to supporting only 64 sensors. We propose a design incorporating daisy-chaining of CSAs via the I2C serial protocol to enable support for 256 sensors. We also demonstrate a rapid prototyping implementation of 128 sensors. The extended work we plan is to implement the prototype on custom Printed Circuit Boards (PCB) and maximize data update frequency. This architecture can find relevance in industries like manufacturing and farming, enhancing precision in the interaction between robots and huma ns/objects.
There have been several developments in renewable resources, standby sources of energy, and storage technologies. Because renewable sources are inconsistent, the best method to ensure supply continuity is to combine t...
详细信息
Threats against critical infrastructure in various sectors (power, water, etc.) are constantly present as their cyber-physical control and communication systems introduce a combination of modern and legacy components....
详细信息
Assessing traffic surveillance data is a prevalent utilization of deep learning methodologies. Video processing techniques were employed to develop the system aimed at determining the velocity of vehicles. The analysi...
详细信息
This paper introduces a simulation preorder among lifted systems, a generalization of finite-dimensional Koopman approximations (also known as approximate immersions) to systems with inputs. It is proved that this sim...
详细信息
This paper introduces a simulation preorder among lifted systems, a generalization of finite-dimensional Koopman approximations (also known as approximate immersions) to systems with inputs. It is proved that this simulation relation implies the containment of both the open- and closed-loop behaviors. Optimization-based sufficient conditions are derived to verify the simulation relation in two special cases: i) a nonlinear (unlifted) system and an affine lifted system and, ii) two affine lifted systems. Numerical examples demonstrate the approach.
Anti-money laundering (AML) refers to a comprehensive framework of laws, regulations, and procedures to prevent bad actors from disguising illegally obtained funds as legitimate income. The AML framework encompasses c...
详细信息
Layered pathwidth is a new graph parameter studied by Bannister et al. (2015). In this paper we present two new results relating layered pathwidth to two types of linear layouts. Our first result shows that, for any g...
详细信息
This paper proposes a unified framework for the stability analysis of discrete-time nonlinear systems from social networks, including the Friedkin-Johnsen opinion model, two opinion dynamics models in the study of soc...
详细信息
In recent years, the number of patients with mental disorders and developmental disabilities has been increasing. Current diagnostic methods for these patients are mainly interviews between clinicians and patients, wh...
详细信息
暂无评论