Spiking Neural Networks (SNNs) are a promising research direction for building power-efficient information processing systems, especially for temporal tasks such as speech recognition. In SNNs, delays refer to the time needed for one spike to travel from one neuron to another. These delays matter because they influence the spike arrival times, and it is well-known that spiking neurons respond more strongly to coincident input spikes. More formally, it has been shown theoretically that plastic delays greatly increase the expressivity in SNNs. Yet, efficient algorithms to learn these delays have been lacking. Here, we propose a new discrete-time algorithm that addresses this issue in deep feedforward SNNs using backpropagation, in an offline manner. To simulate delays between consecutive layers, we use 1D convolutions across time. The kernels contain only a few non-zero weights - one per synapse - whose positions correspond to the delays. These positions are learned together with the weights using the recently proposed Dilated Convolution with Learnable Spacings (DCLS). We evaluated our method on the Spiking Heidelberg Dataset (SHD) and the Spiking Speech Commands (SSC) benchmarks, which require detecting temporal patterns. We used feedforward SNNs with two hidden fully connected layers. We showed that fixed random delays help, and that learning them helps even more. Furthermore, our method outperformed the state-of-the-art in both SHD and SSC without using recurrent connections and with substantially fewer parameters. Our work demonstrates the potential of delay learning in developing accurate and precise models for temporal data processing. Our code is based on PyTorch / SpikingJelly and available at: //github.com/Thvnvtos/SNN-delays
相關內容
As physical layer security evolves to multi-user systems, multi-user interference (MUI) becomes an unavoidable issue. Recently, rate-splitting multiple access (RSMA) emerges as a powerful non-orthogonal transmission framework and interference management strategy with high spectral efficiency. Unlike most works fully treating MUI as noise, we take all users' secrecy rate requirements into consideration and propose an RSMA-based secure beamforming approach to maximize the weighted sum-rate (WSR), where MUI is partially decoded and partially treated as noise. User messages are split and encoded into common and private streams. Each user not only decodes the common stream and the intended private stream, but also tries to eavesdrop other users' private streams. A successive convex approximation (SCA)-based approach is proposed to maximize the instantaneous WSR under perfect channel state information at the transmitter (CSIT). We then propose a joint weighted minimum mean square error and SCA-based alternating optimization algorithm to maximize the weighted ergodic sum-rate under imperfect CSIT. Numerical results demonstrate RSMA achieves better WSR and is more robust to channel errors than conventional multi-user linear precoding technique while ensuring all users' security requirements. Besides, RSMA can satisfy all users' secrecy rate requirements without introducing WSR loss thanks to its powerful interference management capability.
Efficient use of spectral resources will be an important aspect of converged access network deployment. This work analyzes the performance of variable bandwidth Analog Radio-over-Fiber signals transmitted in the unfilled spectral spaces of telecom-grade ROADM channels dedicated for coherent signals transmission over the OpenIreland testbed.
Neuro-symbolic hybrid systems are promising for integrating machine learning and symbolic reasoning, where perception models are facilitated with information inferred from a symbolic knowledge base through logical reasoning. Despite empirical evidence showing the ability of hybrid systems to learn accurate perception models, the theoretical understanding of learnability is still lacking. Hence, it remains unclear why a hybrid system succeeds for a specific task and when it may fail given a different knowledge base. In this paper, we introduce a novel way of characterising supervision signals from a knowledge base, and establish a criterion for determining the knowledge's efficacy in facilitating successful learning. This, for the first time, allows us to address the two questions above by inspecting the knowledge base under investigation. Our analysis suggests that many knowledge bases satisfy the criterion, thus enabling effective learning, while some fail to satisfy it, indicating potential failures. Comprehensive experiments confirm the utility of our criterion on benchmark tasks.
Machine Translation is one of the essential tasks in Natural Language Processing (NLP), which has massive applications in real life as well as contributing to other tasks in the NLP research community. Recently, Transformer -based methods have attracted numerous researchers in this domain and achieved state-of-the-art results in most of the pair languages. In this paper, we report an effective method using a phrase mechanism, PhraseTransformer, to improve the strong baseline model Transformer in constructing a Neural Machine Translation (NMT) system for parallel corpora Vietnamese-Chinese. Our experiments on the MT dataset of the VLSP 2022 competition achieved the BLEU score of 35.3 on Vietnamese to Chinese and 33.2 BLEU scores on Chinese to Vietnamese data. Our code is available at //github.com/phuongnm94/PhraseTransformer.
Federated Learning (FL) is a distributed machine learning technique that allows model training among multiple devices or organizations without sharing data. However, while FL ensures that the raw data is not directly accessible to external adversaries, adversaries can still obtain some statistical information about the data through differential attacks. Differential Privacy (DP) has been proposed, which adds noise to the model or gradients to prevent adversaries from inferring private information from the transmitted parameters. We reconsider the framework of differential privacy federated learning in resource-constrained scenarios (privacy budget and communication resources). We analyze the convergence of federated learning with differential privacy (DPFL) on resource-constrained scenarios and propose an Adaptive Local Steps Differential Privacy Federated Learning (ALS-DPFL) algorithm. We experiment our algorithm on the FashionMNIST and Cifar-10 datasets and achieve quite good performance relative to previous work.
Internet of Things (IoT) technologies have enabled numerous data-driven mobile applications and have the potential to significantly improve environmental monitoring and hazard warnings through the deployment of a network of IoT sensors. However, these IoT devices are often power-constrained and utilize wireless communication schemes with limited bandwidth. Such power constraints limit the amount of information each device can share across the network, while bandwidth limitations hinder sensors' coordination of their transmissions. In this work, we formulate the communication planning problem of IoT sensors that track the state of the environment. We seek to optimize sensors' decisions in collecting environmental data under stringent resource constraints. We propose a multi-agent reinforcement learning (MARL) method to find the optimal communication policies for each sensor that maximize the tracking accuracy subject to the power and bandwidth limitations. MARL learns and exploits the spatial-temporal correlation of the environmental data at each sensor's location to reduce the redundant reports from the sensors. Experiments on wildfire spread with LoRA wireless network simulators show that our MARL method can learn to balance the need to collect enough data to predict wildfire spread with unknown bandwidth limitations.
The synthetic control method (SCM) has become a popular tool for estimating causal effects in policy evaluation, where a single treated unit is observed, and a heterogeneous set of untreated units with pre- and post-policy change data are also observed. However, the synthetic control method faces challenges in accurately predicting post-intervention potential outcome had, contrary to fact, the treatment been withheld, when the pre-intervention period is short or the post-intervention period is long. To address these issues, we propose a novel method that leverages post-intervention information, specifically time-varying correlates of the causal effect called "surrogates", within the synthetic control framework. We establish conditions for identifying model parameters using the proximal inference framework and apply the generalized method of moments (GMM) approach for estimation and inference about the average treatment effect on the treated (ATT). Interestingly, we uncover specific conditions under which exclusively using post-intervention data suffices for estimation within our framework. Moreover, we explore several extensions, including covariates adjustment, relaxing linearity assumptions through non-parametric identification, and incorporating so-called "contaminated" surrogates, which do not exactly satisfy conditions to be valid surrogates but nevertheless can be incorporated via a simple modification of the proposed approach. Through a simulation study, we demonstrate that our method can outperform other synthetic control methods in estimating both short-term and long-term effects, yielding more accurate inferences. In an empirical application examining the Panic of 1907, one of the worst financial crises in U.S. history, we confirm the practical relevance of our theoretical results.
In the prevailing convergence of traditional infrastructure-based deployment (i.e., Telco and industry operational networks) towards evolving deployments enabled by 5G and virtualization, there is a keen interest in elaborating effective security controls to protect these deployments in-depth. By considering key enabling technologies like 5G and virtualization, evolving networks are democratized, facilitating the establishment of point presences integrating different business models ranging from media, dynamic web content, gaming, and a plethora of IoT use cases. Despite the increasing services provided by evolving networks, many cybercrimes and attacks have been launched in evolving networks to perform malicious activities. Due to the limitations of traditional security artifacts (e.g., firewalls and intrusion detection systems), the research on digital forensic data analytics has attracted more attention. Digital forensic analytics enables people to derive detailed information and comprehensive conclusions from different perspectives of cybercrimes to assist in convicting criminals and preventing future crimes. This chapter presents a digital analytics framework for network anomaly detection, including multi-perspective feature engineering, unsupervised anomaly detection, and comprehensive result correction procedures. Experiments on real-world evolving network data show the effectiveness of the proposed forensic data analytics solution.
Non-orthogonal multiple access (NOMA) has come to the fore as a spectrally efficient technique for fifth-generation networks and beyond. At the same time, NOMA faces severe security issues in the presence of untrusted users due to successive interference cancellation (SIC)-based decoding at receivers. In this paper, to make the system model more realistic, we consider the impact of imperfect SIC during the decoding process. Assuming the downlink mode, we focus on designing a secure NOMA communication protocol for the considered system model with two untrusted users. In this regard, we obtain the power allocation bounds to achieve a positive secrecy rate for both near and far users. Analytical expressions of secrecy outage probability (SOP) for both users are derived to analyze secrecy performance. Closed-form approximations of SOPs are also provided to gain analytical insights. Lastly, numerical results have been presented, which validate the exactness of the analysis and reveal the effect of various key parameters on achieved secrecy performance.
Spectral clustering (SC) is a popular clustering technique to find strongly connected communities on a graph. SC can be used in Graph Neural Networks (GNNs) to implement pooling operations that aggregate nodes belonging to the same cluster. However, the eigendecomposition of the Laplacian is expensive and, since clustering results are graph-specific, pooling methods based on SC must perform a new optimization for each new sample. In this paper, we propose a graph clustering approach that addresses these limitations of SC. We formulate a continuous relaxation of the normalized minCUT problem and train a GNN to compute cluster assignments that minimize this objective. Our GNN-based implementation is differentiable, does not require to compute the spectral decomposition, and learns a clustering function that can be quickly evaluated on out-of-sample graphs. From the proposed clustering method, we design a graph pooling operator that overcomes some important limitations of state-of-the-art graph pooling techniques and achieves the best performance in several supervised and unsupervised tasks.
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