Felipe M. G. França

Alan T. L. Bacellar, Mustafa Munir, Felipe M. G. França et al.

Federated Learning (FL) is plagued by two key challenges: high communication overhead and performance collapse on heterogeneous (non-IID) data. Analytic FL (AFL) provides a single-round, data distribution invariant solution, but is limited to linear models. Subsequent non-linear approaches, like DeepAFL, regain accuracy but sacrifice the single-round benefit. In this work, we break this trade-off. We propose SAFLe, a framework that achieves scalable non-linear expressivity by introducing a structured head of bucketed features and sparse, grouped embeddings. We prove this non-linear architecture is mathematically equivalent to a high-dimensional linear regression. This key equivalence allows SAFLe to be solved with AFL's single-shot, invariant aggregation law. Empirically, SAFLe establishes a new state-of-the-art for analytic FL, significantly outperforming both linear AFL and multi-round DeepAFL in accuracy across all benchmarks, demonstrating a highly efficient and scalable solution for federated vision.

F. B. Gonçalves, F. M. G. França, C. L. Amorim

In this study, we propose a variation of the RAdNet for vehicular environments (RAdNet-VE). The proposed scheme extends the message header, mechanism for registering interest, and message forwarding mechanism of RAdNet. To obtain results, we performed simulation experiments involving two use scenarios and communication protocols developed from the Veins framework. Based on results obtained from these experiments, we compare the performance of RAdNet-VE against that of RAdNet, a basic content-centric network (CCN) using reactive data routing, (CCN$_R$), and a basic CCN using proactive data routing, CCN$_P$. These CCNs provide non-cacheable data services. Moreover, the communication radio standards adopted in the scenarios 1 and 2 were respectively IEEE 802.11n and IEEE 802.11p. The results shown that the performance of the RAdNet-VE was superior to than those of RAdNet, CCN$_R$ and CCN$_P$. In this sense, RAdNet-VE protocol (RVEP) presented low communication latencies among nodes of just 20.4ms (scenario 1) and 2.87 ms (scenario 2). Our protocol also presented high data delivery rates, i.e, 83.05\% (scenario 1) and 88.05\% (scenario 2). Based on these and other results presented in this study, we argue that RAdNet-VE is a feasible alternative to CCNs as information-centric network (ICN) model for VANET, because the RVEP satisfies all of the necessary communication requirements.

Shashank Nag, Alan T. L. Bacellar, Zachary Susskind et al.

Vision Transformers have been tremendously successful in computer vision tasks. However, their large computational, memory, and energy demands are a challenge for edge inference on FPGAs -- a field that has seen a recent surge in demand. We recognize the benefits of recent works on logic and Look Up Table (LUT) based networks, such as LogicNets, NeuraLUT, DWN, among others, in offering models that simultaneously reduce both the memory and compute footprints. However, these models natively do not perform well on common vision tasks, such as CIFAR-10/100. In this work, we propose LL-ViT, a novel edge optimized vision transformer design that integrates layers of LUT neurons within the transformer architecture. Based on our characterization that reveals that a majority of model weights and computations are from the channel mixer (MLP layer), we design an alternate LUT-based channel mixer, and simultaneously develop an FPGA-based accelerator for LL-ViT. Contrary to some attempts to replace each multiplication with a table lookup, our architecture utilizes a neural learning approach which natively learns the LUT functions. This approach allows for reduced model sizes, and a computational and energy-efficient inference solution for vision transformer models. Evaluating on edge-suitable workloads, we achieve accuracies of 95.5% on CIFAR-10, 78.8% on CIFAR-100, and 60.9% on Tiny-ImageNet datasets, comparable to the baseline transformer. LL-ViT eliminates over 60% of the model weights and 50% of the multiplications in the model, and achieves 1.9x energy efficiency and 1.3x lower latency over an integer quantized ViT accelerator, while also offering superior throughput against prior works at a 10.9W power budget.

Aluizio S. Lima Filho, Gabriel P. Guarisa, Leopoldo A. D. Lusquino Filho et al.

In order to facilitate the production of codes using WiSARD-based models, LabZero developed an ML library C++/Python called wisardpkg. This library is an MIT-licensed open-source package hosted on GitHub under the license.

Alan T. L. Bacellar, Zachary Susskind, Mauricio Breternitz et al.

We introduce the Differentiable Weightless Neural Network (DWN), a model based on interconnected lookup tables. Training of DWNs is enabled by a novel Extended Finite Difference technique for approximate differentiation of binary values. We propose Learnable Mapping, Learnable Reduction, and Spectral Regularization to further improve the accuracy and efficiency of these models. We evaluate DWNs in three edge computing contexts: (1) an FPGA-based hardware accelerator, where they demonstrate superior latency, throughput, energy efficiency, and model area compared to state-of-the-art solutions, (2) a low-power microcontroller, where they achieve preferable accuracy to XGBoost while subject to stringent memory constraints, and (3) ultra-low-cost chips, where they consistently outperform small models in both accuracy and projected hardware area. DWNs also compare favorably against leading approaches for tabular datasets, with higher average rank. Overall, our work positions DWNs as a pioneering solution for edge-compatible high-throughput neural networks.

Alan T. L. Bacellar, Mugdha P. Jadhao, Shashank Nag et al.

Human Activity Recognition (HAR) is critical for applications in healthcare, fitness, and IoT, but deploying accurate models on resource-constrained devices remains challenging due to high energy and memory demands. This paper demonstrates the application of Differentiable Weightless Neural Networks (DWNs) to HAR, achieving competitive accuracies of 96.34% and 96.67% while consuming only 56nJ and 104nJ per sample, with an inference time of just 5ns per sample. The DWNs were implemented and evaluated on an FPGA, showcasing their practical feasibility for energy-efficient hardware deployment. DWNs achieve up to 926,000x energy savings and 260x memory reduction compared to state-of-the-art deep learning methods. These results position DWNs as a nano-machine learning nanoML model for HAR, setting a new benchmark in energy efficiency and compactness for edge and wearable devices, paving the way for ultra-efficient edge AI.

Shashank Nag, Alan T. L. Bacellar, Zachary Susskind et al.

Transformers are set to become ubiquitous with applications ranging from chatbots and educational assistants to visual recognition and remote sensing. However, their increasing computational and memory demands is resulting in growing energy consumption. Building models with fast and energy-efficient inference is imperative to enable a variety of transformer-based applications. Look Up Table (LUT) based Weightless Neural Networks are faster than the conventional neural networks as their inference only involves a few lookup operations. Recently, an approach for learning LUT networks directly via an Extended Finite Difference method was proposed. We build on this idea, extending it for performing the functions of the Multi Layer Perceptron (MLP) layers in transformer models and integrating them with transformers to propose Quasi Weightless Transformers (QuWeiT). This allows for a computational and energy-efficient inference solution for transformer-based models. On I-ViT-T, we achieve a comparable accuracy of 95.64% on CIFAR-10 dataset while replacing approximately 55% of all the multiplications in the entire model and achieving a 2.2x energy efficiency. We also observe similar savings on experiments with the nanoGPT framework.

Victor de A. Xavier, Felipe M. G. França, Priscila M. V. Lima

Climate change and global warming have been trending topics worldwide since the Eco-92 conference. However, little progress has been made in reducing greenhouse gases (GHGs). The problems and challenges related to emissions are complex and require a concerted and comprehensive effort to address them. Emissions reporting is a critical component of GHG reduction policy and is therefore the focus of this work. The main goal of this work is two-fold: (i) to propose an emission reporting evaluation model to leverage emissions reporting overall quality and (ii) to use artificial intelligence (AI) to support the initiatives that improve emissions reporting. Thus, this work presents an Emissions Reporting Maturity Model (ERMM) for examining, clustering, and analysing data from emissions reporting initiatives to help the cities to deal with climate change and global warming challenges. The Performance Indicator Development Process (PIDP) proposed in this work provides ways to leverage the quality of the available data necessary for the execution of the evaluations identified by the ERMM. Hence, the PIDP supports the preparation of the data from emissions-related databases, the classification of the data according to similarities highlighted by different clustering techniques, and the identification of performance indicator candidates, which are strengthened by a qualitative analysis of selected data samples. Thus, the main goal of ERRM is to evaluate and classify the cities regarding the emission reporting processes, pointing out the drawbacks and challenges faced by other cities from different contexts, and at the end to help them to leverage the underlying emissions-related processes and emissions mitigation initiatives.

Filipe Mutz, Thiago Oliveira-Santos, Avelino Forechi et al.

The localization of self-driving cars is needed for several tasks such as keeping maps updated, tracking objects, and planning. Localization algorithms often take advantage of maps for estimating the car pose. Since maintaining and using several maps is computationally expensive, it is important to analyze which type of map is more adequate for each application. In this work, we provide data for such analysis by comparing the accuracy of a particle filter localization when using occupancy, reflectivity, color, or semantic grid maps. To the best of our knowledge, such evaluation is missing in the literature. For building semantic and colour grid maps, point clouds from a Light Detection and Ranging (LiDAR) sensor are fused with images captured by a front-facing camera. Semantic information is extracted from images with a deep neural network. Experiments are performed in varied environments, under diverse conditions of illumination and traffic. Results show that occupancy grid maps lead to more accurate localization, followed by reflectivity grid maps. In most scenarios, the localization with semantic grid maps kept the position tracking without catastrophic losses, but with errors from 2 to 3 times bigger than the previous. Colour grid maps led to inaccurate and unstable localization even using a robust metric, the entropy correlation coefficient, for comparing online data and the map.