Organic neuromorphic device networks can accelerate neural network algorithms and directly integrate with microfluidic systems or living tissues. Proposed devices based on the bio-compatible conductive polymer PEDOT:PSS have shown high switching speeds and low energy demand. However, as electrochemical systems, they are prone to self-discharge through parasitic electrochemical reactions. Therefore, the network's synapses forget their trained conductance states over time. This work integrates single-device high-resolution charge transport models to simulate neuromorphic device networks and analyze the impact of self-discharge on network performance. Simulation of a single-layer nine-pixel image classification network reveals no significant impact of self-discharge on training efficiency. And, even though the network's weights drift significantly during self-discharge, its predictions remain 100\% accurate for over ten hours. On the other hand, a multi-layer network for the approximation of the circle function is shown to degrade significantly over twenty minutes with a final mean-squared-error loss of 0.4. We propose to counter the effect by periodically reminding the network based on a map between a synapse's current state, the time since the last reminder, and the weight drift. We show that this method with a map obtained through validated simulations can reduce the effective loss to below 0.1 even with worst-case assumptions. Finally, while the training of this network is affected by self-discharge, a good classification is still obtained. Electrochemical organic neuromorphic devices have not been integrated into larger device networks. This work predicts their behavior under nonideal conditions, mitigates the worst-case effects of parasitic self-discharge, and opens the path toward implementing fast and efficient neural networks on organic neuromorphic hardware.
相關內容
Networking：IFIP International Conferences on Networking。
Explanation：國(guo)際網絡會議。
Publisher：IFIP。
SIT：
Self-paced curriculum learning (SCL) has demonstrated its great potential in computer vision, natural language processing, etc. During training, it implements easy-to-hard sampling based on online estimation of data difficulty. Most SCL methods commonly adopt a loss-based strategy of estimating data difficulty and deweighting the `hard' samples in the early training stage. While achieving success in a variety of applications, SCL stills confront two challenges in a medical image analysis task, such as universal lesion detection, featuring insufficient and highly class-imbalanced data: (i) the loss-based difficulty measurer is inaccurate; ii) the hard samples are under-utilized from a deweighting mechanism. To overcome these challenges, in this paper we propose a novel mixed-order self-paced curriculum learning (Mo-SCL) method. We integrate both uncertainty and loss to better estimate difficulty online and mix both hard and easy samples in the same mini-batch to appropriately alleviate the problem of under-utilization of hard samples. We provide a theoretical investigation of our method in the context of stochastic gradient descent optimization and extensive experiments based on the DeepLesion benchmark dataset for universal lesion detection (ULD). When applied to two state-of-the-art ULD methods, the proposed mixed-order SCL method can provide a free boost to lesion detection accuracy without extra special network designs.
High-quality education is one of the keys to achieving a more sustainable world. In contrast to traditional face-to-face classroom education, online education enables us to record and research a large amount of learning data for offering intelligent educational services. Knowledge Tracing (KT), which aims to monitor students' evolving knowledge state in learning, is the fundamental task to support these intelligent services. In recent years, an increasing amount of research is focused on this emerging field and considerable progress has been made. In this survey, we categorize existing KT models from a technical perspective and investigate these models in a systematic manner. Subsequently, we review abundant variants of KT models that consider more strict learning assumptions from three phases: before, during, and after learning. To better facilitate researchers and practitioners working on this field, we open source two algorithm libraries: EduData for downloading and preprocessing KT-related datasets, and EduKTM with extensible and unified implementation of existing mainstream KT models. Moreover, the development of KT cannot be separated from its applications, therefore we further present typical KT applications in different scenarios. Finally, we discuss some potential directions for future research in this fast-growing field.
When dealing with tabular data, models based on decision trees are a popular choice due to their high accuracy on these data types, their ease of application, and explainability properties. However, when it comes to graph-structured data, it is not clear how to apply them effectively, in a way that incorporates the topological information with the tabular data available on the vertices of the graph. To address this challenge, we introduce Decision Trees with Dynamic Graph Features (TREE-G). Rather than only using the pre-defined given features in the data, TREE-G acts on dynamic features, which are computed as the graph traverses the tree. These dynamic features combine the vertex features with the topological information, as well as the cumulative information learned by the tree. Therefore, the features adapt to the predictive task and the graph in hand. We analyze the theoretical properties of TREE-G and demonstrate its benefits empirically on multiple graph and node prediction benchmarks. In these experiments,TREE-G consistently outperformed other tree-based models and often outperformed other graph-learning algorithms such as Graph Neural Networks (GNNs) and Graph Kernels, sometimes by large margins. Finally, we also provide an explainability mechanism for TREE-G, and demonstrate that it can provide informative and intuitive explanations.
Front-end electronics equipped with high-speed digitizers are being used and proposed for future nuclear detectors. Recent literature reveals that deep learning models, especially one-dimensional convolutional neural networks, are promising when dealing with digital signals from nuclear detectors. Simulations and experiments demonstrate the satisfactory accuracy and additional benefits of neural networks in this area. However, specific hardware accelerating such models for online operations still needs to be studied. In this work, we introduce PulseDL-II, a system-on-chip (SoC) specially designed for applications of event feature (time, energy, etc.) extraction from pulses with deep learning. Based on the previous version, PulseDL-II incorporates a RISC CPU into the system structure for better functional flexibility and integrity. The neural network accelerator in the SoC adopts a three-level (arithmetic unit, processing element, neural network) hierarchical architecture and facilitates parameter optimization of the digital design. Furthermore, we devise a quantization scheme compatible with deep learning frameworks (e.g., TensorFlow) within a selected subset of layer types. We validate the correct operations of PulseDL-II on field programmable gate arrays (FPGA) alone and with an experimental setup comprising a direct digital synthesis (DDS) and analog-to-digital converters (ADC). The proposed system achieved 60 ps time resolution and 0.40% energy resolution at signal to noise ratio (SNR) of 47.4 dB.
This work develops a novel approach towards performance guarantees for all links in arbitrarily large wireless networks. It introduces spatial regulation properties for stationary spatial point processes and develops the first steps of a calculus for this regulation, which can be seen as an extension to space of the classical network calculus. Specifically, two classes of regulations are defined: one includes ball regulation and shot-noise regulation, which are shown equivalent and leads to upper bounds on the interference power; the other one includes void regulation, which lower constraints the signal power. These regulations are defined both in the strong and weak sense: the former requires the regulations to hold everywhere in space, whereas the latter only requires the regulations to hold as observed by a jointly stationary point process. Using this approach, we derive performance guarantees in device-to-device, ad hoc, and cellular networks under proper regulations, respectively. We give universal bounds on the SINR for all links, which gives link service guarantees based on information theoretic achievability. They are combined with classical network calculus to provide end-to-end latency guarantees for all packets in wireless queuing networks. Such guarantees do not exist in networks that are not spatially regulated, e.g., Poisson networks
The real-time processing of time series signals is a critical issue for many real-life applications. The idea of real-time processing is especially important in audio domain as the human perception of sound is sensitive to any kind of disturbance in perceived signals, especially the lag between auditory and visual modalities. The rise of deep learning (DL) models complicated the landscape of signal processing. Although they often have superior quality compared to standard DSP methods, this advantage is diminished by higher latency. In this work we propose novel method for minimization of inference time latency and memory consumption, called Short-Term Memory Convolution (STMC) and its transposed counterpart. The main advantage of STMC is the low latency comparable to long short-term memory (LSTM) networks. Furthermore, the training of STMC-based models is faster and more stable as the method is based solely on convolutional neural networks (CNNs). In this study we demonstrate an application of this solution to a U-Net model for a speech separation task and GhostNet model in acoustic scene classification (ASC) task. In case of speech separation we achieved a 5-fold reduction in inference time and a 2-fold reduction in latency without affecting the output quality. The inference time for ASC task was up to 4 times faster while preserving the original accuracy.
The SpMV kernel is characterized by high performance variation per input matrix and computing platform. While GPUs were considered State-of-the-Art for SpMV, with the emergence of advanced multicore CPUs and low-power FPGA accelerators, we need to revisit its performance and energy efficiency. This paper provides a high-level SpMV performance analysis based on structural features of matrices related to common bottlenecks of memory-bandwidth intensity, low ILP, load imbalance and memory latency overheads. Towards this, we create a wide artificial matrix dataset that spans these features and study the performance of different storage formats in nine modern HPC platforms; five CPUs, three GPUs and an FPGA. After validating our proposed methodology using real-world matrices, we analyze our extensive experimental results and draw key insights on the competitiveness of different target architectures for SpMV and the impact of each feature/bottleneck on its performance.
The potential of Model Predictive Control in buildings has been shown many times, being successfully used to achieve various goals, such as minimizing energy consumption or maximizing thermal comfort. However, mass deployment has thus far failed, in part because of the high engineering cost of obtaining and maintaining a sufficiently accurate model. This can be addressed by using adaptive data-driven approaches. The idea of using behavioral systems theory for this purpose has recently found traction in the academic community. In this study, we compare variations thereof with different amounts of data used, different regularization weights, and different methods of data selection. Autoregressive models with exogenous inputs (ARX) are used as a well-established reference. All methods are evaluated by performing iterative system identification on two long-term data sets from real occupied buildings, neither of which include artificial excitation for the purpose of system identification. We find that: (1) Sufficient prediction accuracy is achieved with all methods. (2) The ARX models perform slightly better, while having the additional advantages of fewer tuning parameters and faster computation. (3) Adaptive and non-adaptive schemes perform similarly. (4) The regularization weights of the behavioral systems theory methods show the expected trade-off characteristic with an optimal middle value. (5) Using the most recent data yields better performance than selecting data with similar weather as the day to be predicted. (6) More data improves the model performance.
Deep neural networks (DNNs) have achieved unprecedented success in the field of artificial intelligence (AI), including computer vision, natural language processing and speech recognition. However, their superior performance comes at the considerable cost of computational complexity, which greatly hinders their applications in many resource-constrained devices, such as mobile phones and Internet of Things (IoT) devices. Therefore, methods and techniques that are able to lift the efficiency bottleneck while preserving the high accuracy of DNNs are in great demand in order to enable numerous edge AI applications. This paper provides an overview of efficient deep learning methods, systems and applications. We start from introducing popular model compression methods, including pruning, factorization, quantization as well as compact model design. To reduce the large design cost of these manual solutions, we discuss the AutoML framework for each of them, such as neural architecture search (NAS) and automated pruning and quantization. We then cover efficient on-device training to enable user customization based on the local data on mobile devices. Apart from general acceleration techniques, we also showcase several task-specific accelerations for point cloud, video and natural language processing by exploiting their spatial sparsity and temporal/token redundancy. Finally, to support all these algorithmic advancements, we introduce the efficient deep learning system design from both software and hardware perspectives.
Since deep neural networks were developed, they have made huge contributions to everyday lives. Machine learning provides more rational advice than humans are capable of in almost every aspect of daily life. However, despite this achievement, the design and training of neural networks are still challenging and unpredictable procedures. To lower the technical thresholds for common users, automated hyper-parameter optimization (HPO) has become a popular topic in both academic and industrial areas. This paper provides a review of the most essential topics on HPO. The first section introduces the key hyper-parameters related to model training and structure, and discusses their importance and methods to define the value range. Then, the research focuses on major optimization algorithms and their applicability, covering their efficiency and accuracy especially for deep learning networks. This study next reviews major services and toolkits for HPO, comparing their support for state-of-the-art searching algorithms, feasibility with major deep learning frameworks, and extensibility for new modules designed by users. The paper concludes with problems that exist when HPO is applied to deep learning, a comparison between optimization algorithms, and prominent approaches for model evaluation with limited computational resources.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191