Search

Low-precision weights and activations in deep neural networks (DNNs) outperform their full-precision counterparts in terms of hardware efficiency. When implemented with low-precision operations, specifically in the extreme case where network parameters are binarized (i.e. BNNs), the two most frequently mentioned benefits of quantization are reduced memory consumption and a faster inference process. In this paper, we introduce a third advantage of very low-precision neural networks: improved fault-tolerance attribute. We investigate the impact of memory faults on state-of-the-art binary neural networks (BNNs) through comprehensive analysis. Despite the inclusion of floating-point parameters in BNN architectures to improve accuracy, our findings reveal that BNNs are highly sensitive to deviations in these parameters caused by memory faults. In light of this crucial finding, we propose a technique to improve BNN dependability by restricting the range of float parameters through a novel deliberately uniform quantization. The introduced quantization technique results in a reduction in the proportion of floating-point parameters utilized in the BNN, without incurring any additional computational overheads during the inference stage. The extensive experimental fault simulation on the proposed BNN architecture (i.e. ZOBNN) reveal a remarkable 5X enhancement in robustness compared to conventional floating-point DNN. Notably, this improvement is achieved without incurring any computational overhead. Crucially, this enhancement comes without computational overhead. \ToolName~excels in critical edge applications characterized by limited computational resources, prioritizing both dependability and real-time performance.

YOLO is a deep neural network (DNN) model presented for robust real-time object detection following the one-stage inference approach. It outperforms other real-time object detectors in terms of speed and accuracy by a wide margin. Nevertheless, since YOLO is developed upon a DNN backbone with numerous parameters, it will cause excessive memory load, thereby deploying it on memory-constrained devices is a severe challenge in practice. To overcome this limitation, model compression techniques, such as quantizing parameters to lower-precision values, can be adopted. As the most recent version of YOLO, YOLOv7 achieves such state-of-the-art performance in speed and accuracy in the range of 5 FPS to 160 FPS that it surpasses all former versions of YOLO and other existing models in this regard. So far, the robustness of several quantization schemes has been evaluated on older versions of YOLO. These methods may not necessarily yield similar results for YOLOv7 as it utilizes a different architecture. In this paper, we conduct in-depth research on the effectiveness of a variety of quantization schemes on the pre-trained weights of the state-of-the-art YOLOv7 model. Experimental results demonstrate that using 4-bit quantization coupled with the combination of different granularities results in ~3.92x and ~3.86x memory-saving for uniform and non-uniform quantization, respectively, with only 2.5% and 1% accuracy loss compared to the full-precision baseline model., Comment: Presented at the "2023 28th International Computer Conference, Computer Society of Iran (CSICC)" and indexed in IEEE

Compared to the wide array of advanced Monte Carlo methods supported by modern probabilistic programming languages (PPLs), PPL support for variational inference (VI) is less developed: users are typically limited to a predefined selection of variational objectives and gradient estimators, which are implemented monolithically (and without formal correctness arguments) in PPL backends. In this paper, we propose a more modular approach to supporting variational inference in PPLs, based on compositional program transformation. In our approach, variational objectives are expressed as programs, that may employ first-class constructs for computing densities of and expected values under user-defined models and variational families. We then transform these programs systematically into unbiased gradient estimators for optimizing the objectives they define. Our design enables modular reasoning about many interacting concerns, including automatic differentiation, density accumulation, tracing, and the application of unbiased gradient estimation strategies. Additionally, relative to existing support for VI in PPLs, our design increases expressiveness along three axes: (1) it supports an open-ended set of user-defined variational objectives, rather than a fixed menu of options; (2) it supports a combinatorial space of gradient estimation strategies, many not automated by today's PPLs; and (3) it supports a broader class of models and variational families, because it supports constructs for approximate marginalization and normalization (previously introduced only for Monte Carlo inference). We implement our approach in an extension to the Gen probabilistic programming system (genjax.vi, implemented in JAX), and evaluate on several deep generative modeling tasks, showing minimal performance overhead vs. hand-coded implementations and performance competitive with well-established open-source PPLs.

This article presents GenSQL, a probabilistic programming system for querying probabilistic generative models of database tables. By augmenting SQL with only a few key primitives for querying probabilistic models, GenSQL enables complex Bayesian inference workflows to be concisely implemented. GenSQL's query planner rests on a unified programmatic interface for interacting with probabilistic models of tabular data, which makes it possible to use models written in a variety of probabilistic programming languages that are tailored to specific workflows. Probabilistic models may be automatically learned via probabilistic program synthesis, hand-designed, or a combination of both. GenSQL is formalized using a novel type system and denotational semantics, which together enable us to establish proofs that precisely characterize its soundness guarantees. We evaluate our system on two case real-world studies -- an anomaly detection in clinical trials and conditional synthetic data generation for a virtual wet lab -- and show that GenSQL more accurately captures the complexity of the data as compared to common baselines. We also show that the declarative syntax in GenSQL is more concise and less error-prone as compared to several alternatives. Finally, GenSQL delivers a 1.7-6.8x speedup compared to its closest competitor on a representative benchmark set and runs in comparable time to hand-written code, in part due to its reusable optimizations and code specialization., Comment: 54 pages, 30 figures, 1 table, published at PLDI 2024

The imperative to deploy Deep Neural Network (DNN) models on resource-constrained edge devices, spurred by privacy concerns, has become increasingly apparent. To facilitate the transition from cloud to edge computing, this paper introduces a technique that effectively reduces the memory footprint of DNNs, accommodating the limitations of resource-constrained edge devices while preserving model accuracy. Our proposed technique, named Post-Training Intra-Layer Multi-Precision Quantization (PTILMPQ), employs a post-training quantization approach, eliminating the need for extensive training data. By estimating the importance of layers and channels within the network, the proposed method enables precise bit allocation throughout the quantization process. Experimental results demonstrate that PTILMPQ offers a promising solution for deploying DNNs on edge devices with restricted memory resources. For instance, in the case of ResNet50, it achieves an accuracy of 74.57\% with a memory footprint of 9.5 MB, representing a 25.49\% reduction compared to previous similar methods, with only a minor 1.08\% decrease in accuracy., Comment: The 25th International Symposium on Quality Electronic Design (ISQED'24)

The commensal symbiotic radio (CSR) system is proposed as a novel solution for connecting systems through green communication networks. This system enables us to establish secure, ubiquitous, and unlimited connectivity, which is a goal of 6G. The base station uses MIMO antennas to transmit its signal. Passive IoT devices, called symbiotic backscatter devices (SBDs), receive the signal and use it to charge their power supply. When the SBDs have data to transmit, they modulate the information onto the received ambient RF signal and send it to the symbiotic user equipment, which is a typical active device. The main purpose is to enhance energy efficiency in this network by minimizing energy consumption (EC) while ensuring the minimum required throughput for SBDs. To achieve this, we propose a new scheduling scheme called Timing-SR that optimally allocates resources to SBDs. The main optimization problem involves non-convex objective functions and constraints. To solve this, we use mathematical techniques and introduce a new approach called sequential quadratic and conic quadratic representation to relax and discipline the problem, leading to reducing its complexity and convergence time. The simulation results demonstrate that the proposed approach outperforms other outlined schemes in reducing EC.

In this paper, we employ active simultaneously transmitting and reflecting reconfigurable intelligent surface (ASRIS) to aid in establishing and enhancing communication within a commensal symbiotic radio (CSR) network. Unlike traditional RIS, ASRIS not only ensures coverage in an omni directional manner but also amplifies received signals, consequently elevating overall network performance. in the first phase, base station (BS) with active massive MIMO antennas, send ambient signal to SBDs. In the first phase, the BS transmits ambient signals to the symbiotic backscatter devices (SBDs), and after harvesting the energy and modulating their information onto the signal carrier, the SBDs send Backscatter signals back to the BS. In this scheme, we employ the Backscatter Relay system to facilitate the transmission of information from the SBDs to the symbiotic User Equipments (SUEs) with the assistance of the BS. In the second phase, the BS transmits information signals to the SUEs after eliminating interference using the Successive Interference Cancellation (SIC) method. ASRIS is employed to establish communication among SUEs lacking a line of sight (LoS) and to amplify power signals for SUEs with a LoS connection to the BS. It is worth noting that we use NOMA for multiple access in all network. The main goal of this paper is to maximize the sum throughput between all users. To achieve this, we formulate an optimization problem with variables including active beamforming coefficients at the BS and ASRIS, as well as the phase adjustments of ASRIS and scheduling parameters between the first and second phases. To model this optimization problem, we employ three deep reinforcement learning (DRL) methods, namely PPO, TD3, and A3C. Finally, the mentioned methods are simulated and compared with each other., Comment: This article will be submitted to the Transactions journal

The optical absorption spectrum of $C_{60}$-dimers and polymers was investigated by Kikuo et al. in 1996\cite{harigaya1996charge}. As a compliment to these earlier studies, the optical absorption spectrum of the $C_{70}$ fullerene has been investigated in the present study. The main purpose was then to compare the absorption spectrum of the $C_{70}$-dimers and trimers and, more specifically, to clarify the effect of these molecular structures on the absorption spectrum. What is most important and decisive is then the value of the conjugation parameter of these $C_{70}$-based molecules. In the present study, a tight-binding model was used in calculating the optical absorption spectra of both $C_{70}$ dimers and polymers, as well as $C_{70}$ trimers and polymers. The change in conjugation parameter for each of these species was found to cause variations in the corresponding optical absorption spectrum. It was found that the absorption tensor of the $C_{70}$ trimer and the polymer was, depending on the value of the conjugation parameters $b=0.5$ and $b=0.8$. The situation was almost the same for the conjugation parameters $b=0.1$ and $b=0.2$. In addition, the value of the band gap was also different depending on the different conjugation parameters, with a reduced value for the larger values of this parameter. As a conclusion, smaller values of the conjugation parameter were not found to have a large effect on the absorption spectrum of the $C_{70}$-dimers and trimers, or in other words, the effect was hardly visible. On the contrary, the larger values caused a drastic change in the optical absorption spectrum of the $C_{70}$-dimers and trimers., Comment: 6 pages, 6 figures

Robots cannot yet match humans' ability to rapidly learn the shapes of novel 3D objects and recognize them robustly despite clutter and occlusion. We present Bayes3D, an uncertainty-aware perception system for structured 3D scenes, that reports accurate posterior uncertainty over 3D object shape, pose, and scene composition in the presence of clutter and occlusion. Bayes3D delivers these capabilities via a novel hierarchical Bayesian model for 3D scenes and a GPU-accelerated coarse-to-fine sequential Monte Carlo algorithm. Quantitative experiments show that Bayes3D can learn 3D models of novel objects from just a handful of views, recognizing them more robustly and with orders of magnitude less training data than neural baselines, and tracking 3D objects faster than real time on a single GPU. We also demonstrate that Bayes3D learns complex 3D object models and accurately infers 3D scene composition when used on a Panda robot in a tabletop scenario.

This paper introduces a consensus-based generalized multi-population aggregative game coordination approach with application to electric vehicles charging under transmission line constraints. The algorithm enables agents to seek an equilibrium solution while considering the limited infrastructure capacities that impose coupling constraints among the users. The Nash-seeking algorithm consists of two interrelated iterations. In the upper layer, population coordinators collaborate for a distributed estimation of the coupling aggregate term in the agents' cost function and the associated Lagrange multiplier of the coupling constraint, transmitting the latest updated values to their population's agents. In the lower layer, each agent updates its best response based on the most recent information received and communicates it back to its population coordinator. For the case when the agents' best response mappings are non-expansive, we prove the algorithm's convergence to the generalized Nash equilibrium point of the game. Simulation results demonstrate the algorithm's effectiveness in achieving equilibrium in the presence of a coupling constraint., Comment: 8 pages, 5 figures, journal

Wireless localization is essential for tracking objects in indoor environments. Internet of Things (IoT) enables localization through its diverse wireless communication protocols. In this paper, a hybrid section-based indoor localization method using a developed Radio Frequency Identification (RFID) tracking device and multiple IoT wireless technologies is proposed. In order to reduce the cost of the RFID tags, the tags are installed only on the borders of each section. The RFID tracking device identifies the section, and the proposed wireless hybrid method finds the location of the object inside the section. The proposed hybrid method is analytically driven by linear location estimates obtained from different IoT wireless technologies. The experimental results using developed RFID tracking device and RSSI-based localization for Bluetooth, WiFi and ZigBee technologies verifies the analytical results.

Image segmentation is a branch of computer vision that is widely used in real world applications including biomedical image processing. With recent advancement of deep learning, image segmentation has achieved at a very high level performance. Recently, UNet architecture is found as the core of novel deep learning segmentation methods. In this paper we implement UNet architecture from scratch with using basic blocks in Pytorch and evaluate its performance on multiple biomedical image datasets. We also use transfer learning to apply novel modified UNet segmentation packages on the biomedical image datasets. We fine tune the pre-trained transferred model with each specific dataset. We compare its performance with our fundamental UNet implementation. We show that transferred learning model has better performance in image segmentation than UNet model that is implemented from scratch.

Many aerospace and automotive applications use FPGAs in their designs due to their low power and reconfigurability requirements. Meanwhile, such applications also pose a high standard on system reliability, which makes the early-stage reliability analysis for FPGA-based designs very critical. In this paper, we present a framework that enables fast and accurate early-stage analysis of soft error vulnerability for small FPGA-based designs. Our framework first extracts the post-synthesis netlist from an FPGA design. Then it inserts the bit-flip configuration faults into the design netlist using our proposed interface software. After that, it seamlessly feeds the golden copy and fault copies of the netlist into the open source simulator Verilator for cycle-accurate simulation. Finally, it generates a histogram of vulnerability scores of the original design to guide the reliability analysis. Experimental results show that our framework runs up to 53x faster than the Xilinx Vivado fault simulation with cycle-level accuracy, when analyzing the injected bit-flip faults on the ITC'99 benchmarks.

The problem of chemotherapy treatment optimization can be defined in order to minimize the size of the tumor without endangering the patient's health; therefore, chemotherapy requires to achieve a number of objectives, simultaneously. For this reason, the optimization problem turns to a multi-objective problem. In this paper, a multi-objective meta-heuristic method is provided for cancer chemotherapy with the aim of balancing between two objectives: the amount of toxicity and the number of cancerous cells. The proposed method uses mathematical models in order to measure the drug concentration, tumor growth and the amount of toxicity. This method utilizes a Multi-Objective Particle Swarm Optimization (MOPSO) algorithm to optimize cancer chemotherapy plan using cell-cycle specific drugs. The proposed method can be a good model for personalized medicine as it returns a set of solutions as output that have balanced between different objectives and provided the possibility to choose the most appropriate therapeutic plan based on some information about the status of the patient. Experimental results confirm that the proposed method is able to explore the search space efficiently in order to find out the suitable treatment plan with minimal side effects. This main objective is provided using a desirable designing of chemotherapy drugs and controlling the injection dose. Moreover, results show that the proposed method achieve to a better therapeutic performance compared to a more recent similar method [1].

This paper presents an overview of the integration of deep machine learning (DL) in FPGA CAD design flow, focusing on high-level and logic synthesis, placement, and routing. Our analysis identifies key research areas that require more attention in FPGA CAD design, including the development of open-source benchmarks optimized for end-to-end machine learning experiences and the potential of knowledge-sharing among researchers and industry practitioners to incorporate more intelligence in FPGA CAD decision-making steps. By providing insights into the integration of deep machine learning in FPGA CAD flow, this paper aims to inform future research directions in this exciting and rapidly evolving field.

Approximate computing (AC) has become a prominent solution to improve the performance, area, and power/energy efficiency of a digital design at the cost of output accuracy. We propose a novel scalable approximate multiplier that utilizes a lookup table-based compensation unit. To improve energy-efficiency, input operands are truncated to a reduced bitwidth representation (e.g., h bits) based on their leading one positions. Then, a curve-fitting method is employed to map the product term to a linear function, and a piecewise constant error-correction term is used to reduce the approximation error. For computing the piecewise constant error-compensation term, we partition the function space into M segments and compute the compensation factor for each segment by averaging the errors in the segment. The multiplier supports various degrees of truncation and error-compensation to exploit accuracy-efficiency trade-off. The proposed approximate multiplier offers better error metrics such as mean and standard deviation of absolute relative error (MARED and StdARED) compare to a state-of-the-art integer approximate multiplier. The proposed approximate multiplier improves the MARED and StdARED by about 38% and 32% when its energy consumption is about equal to the state-of-the-art approximate multiplier. Moreover, the performance of the proposed approximate multiplier is evaluated in image classification applications using a Deep Neural Network (DNN). The results indicate that the degradation of DNN accuracy is negligible especially due to the compensation properties of our approximate multiplier.