相关论文: Analog Implementation of the Softmax Function

We experimentally assess the suitability of transmon qubits with fixed frequencies and fixed interactions for the realization of analogue quantum simulations of spin systems. We test a set of necessary criteria for this goal on a commercial…

This article is devoted to one particular case of using universal accelerated proximal envelopes to obtain computationally efficient accelerated versions of methods used to solve various optimization problem setups. We propose a proximally…

The softmax function is a cornerstone of multi-class classification, integral to a wide range of machine learning applications, from large-scale retrieval and ranking models to advanced large language models. However, its computational cost…

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of tasks, but their deployment is often constrained by substantial memory footprints and computational costs. While prior work has achieved…

We propose a field-free switching SOT-MRAM concept that is integration friendly and allows for separate optimization of the field component and SOT/MTJ stack properties. We demonstrate it on a 300 mm wafer, using CMOS-compatible processes,…

This paper presents an extension of the BrainScaleS accelerated analog neuromorphic hardware model. The scalable neuromorphic architecture is extended by the support for multi-compartment models and non-linear dendrites. These features are…

Recent advances in machine learning and neuro-inspired systems enabled the increased interest in efficient pattern recognition at the edge. A wide variety of applications, such as near-sensor classification, require fast and low-power…

Exploring the limits of an Analog and Mixed Signal (AMS) circuit by driving appropriate inputs has been a serious challenge to the industry. Doing an exhaustive search of the entire input state space is a time-consuming exercise and the…

Submodular optimization with bandit feedback has recently been studied in a variety of contexts. In a number of real-world applications such as diversified recommender systems and data summarization, the submodular function exhibits…

The concept of scalability analysis of numerical parallel applications has been revisited, with the specific goals defined for the performance estimation of research applications. A series of Community Climate Model System (CCSM) numerical…

Current soft processor architectures for FPGAs do not utilize the potential of the massive parallelism available. FPGAs now support many thousands of embedded floating point operators, and have similar computational densities to GPGPUs.…

Symmetric submodular functions are an important family of submodular functions capturing many interesting cases including cut functions of graphs and hypergraphs. Maximization of such functions subject to various constraints receives little…

We propose a simple modification to the conventional attention mechanism applied by Transformers: Instead of quantifying pairwise query-key similarity with scaled dot-products, we quantify it with the logarithms of scaled dot-products of…

FPMax implements four FPUs optimized for latency or throughput workloads in two precisions, fabricated in 28nm UTBB FDSOI. Each unit's parameters, e.g pipeline stages, booth encoding etc., were optimized to yield 1.42ns latency at…

Exactly computing the full output distribution of linear optical circuits remains a challenge, as existing methods are either time-efficient but memory-intensive or memory-efficient but slow. Moreover, any realistic simulation must account…

Noise in existing quantum processors only enables an approximation to ideal quantum computation. However, these approximations can be vastly improved by error mitigation, for the computation of expectation values, as shown by small-scale…

The large-N expansion technique is tested via an anomalous, soft-core potential which admits the tunneling through its central barrier. The precision of the approximation is found sensitive to the asymptotic component of the interaction.…

We propose an approach to assess the synchronization of rigidly mounted sensors based on their rotational motion. Using function similarity measures combined with a sliding window approach, our approach is capable of estimating time-varying…

Spectrally-efficient communication systems rely on the use of multi-level modulation formats. At the receiver side, a demodulator is often used to extract soft information about the transmitted bits. Such a demodulator is typically…

This article is devoted to one particular case of using universal accelerated proximal envelopes to obtain computationally efficient accelerated versions of methods used to solve various optimization problem setups. In this paper, we…