اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدNeural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices
81
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Recent works propose neural network- (NN-) inspired analog-to-digital converters (NNADCs) and demonstrate their great potentials in many emerging applications. These NNADCs often rely on resistive random-access memory (RRAM) devices to realize the NN operations and require high-precision RRAM cells (6~12-bit) to achieve a moderate quantization resolution (4~8-bit). Such optimistic assumption of RRAM resolution, however, is not supported by fabrication data of RRAM arrays in large-scale production process. In this paper, we propose an NN-inspired super-resolution ADC based on low-precision RRAM devices by taking the advantage of a co-design methodology that combines a pipelined hardware architecture with a custom NN training framework. Results obtained from SPICE simulations demonstrate that our method leads to robust design of a 14-bit super-resolution ADC using 3-bit RRAM devices with improved power and speed performance and competitive figure-of-merits (FoMs). In addition to the linear uniform quantization, the proposed ADC can also support configurable high-resolution nonlinear quantization with high conversion speed and low conversion energy, enabling future intelligent analog-to-information interfaces for near-sensor analytics and processing.
قيم البحث
اقرأ أيضاً
In a growing number of applications, there is a need to digitize signals whose spectral characteristics are challenging for traditional Analog-to-Digital Converters (ADCs). Examples, among others, include systems where the ADC must acquire at once a
very wide but sparsely and dynamically occupied bandwidth supporting diverse services, as well as systems where the signal of interest is subject to strong narrowband co-channel interference. In such scenarios, the resolution requirements can be prohibitively high. As an alternative, the recently proposed modulo-ADC architecture can in principle require dramatically fewer bits in the conversation to obtain the target fidelity, but requires that information about the spectrum be known and explicitly taken into account by the analog and digital processing in the converter, which is frequently impractical. To address this limitation, we develop a blind version of the architecture that requires no such knowledge in the converter, without sacrificing performance. In particular, it features an automatic modulo-level adjustment and a fully adaptive modulo unwrapping mechanism, allowing it to asymptotically match the characteristics of the unknown input signal. In addition to detailed analysis, simulations demonstrate the attractive performance characteristics in representative settings.
We consider the problem of mapping digital data encoded on a quantum register to analog amplitudes in parallel. It is shown to be unlikely that a fully unitary polynomial-time quantum algorithm exists for this problem; NP becomes a subset of BQP if i
t exists. In the practical point of view, we propose a nonunitary linear-time algorithm using quantum decoherence. It tacitly uses an exponentially large physical resource, which is typically a huge number of identical molecules. Quantumness of correlation appearing in the process of the algorithm is also discussed.
The wide bandwidth and large number of antennas used in millimeter wave systems put a heavy burden on the power consumption at the receiver. In this paper, using an additive quantization noise model, the effect of analog-digital conversion (ADC) reso
lution and bandwidth on the achievable rate is investigated for a multi-antenna system under a receiver power constraint. Two receiver architectures, analog and digital combining, are compared in terms of performance. Results demonstrate that: (i) For both analog and digital combining, there is a maximum bandwidth beyond which the achievable rate decreases; (ii) Depending on the operating regime of the system, analog combiner may have higher rate but digital combining uses less bandwidth when only ADC power consumption is considered, (iii) digital combining may have higher rate when power consumption of all the components in the receiver front-end are taken into account.
The paper proposes a method to convert a deep learning object detector into an equivalent spiking neural network. The aim is to provide a conversion framework that is not constrained to shallow network structures and classification problems as in sta
te-of-the-art conversion libraries. The results show that models of higher complexity, such as the RetinaNet object detector, can be converted with limited loss in performance.
Accessible machine learning algorithms, software, and diagnostic tools for energy-efficient devices and systems are extremely valuable across a broad range of application domains. In scientific domains, real-time near-sensor processing can drasticall
y improve experimental design and accelerate scientific discoveries. To support domain scientists, we have developed hls4ml, an open-source software-hardware codesign workflow to interpret and translate machine learning algorithms for implementation with both FPGA and ASIC technologies. We expand on previous hls4ml work by extending capabilities and techniques towards low-power implementations and increased usability: new Python APIs, quantization-aware pruning, end-to-end FPGA workflows, long pipeline kernels for low power, and new device backends include an ASIC workflow. Taken together, these and continued efforts in hls4ml will arm a new generation of domain scientists with accessible, efficient, and powerful tools for machine-learning-accelerated discovery.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
