1,720,979 research outputs found
In-Memory Principal Component Analysis by Analogue Closed-Loop Eigendecomposition
Full text linkMachine learning (ML) techniques such as principal component analysis (PCA) have become pivotal in enabling efficient processing of big data in an increasing number of applications. However, the data-intensive computation in PCA causes large energy consumption in conventional von Neumann computers. In-memory computing (IMC) significantly improves throughput and energy efficiency by eliminating the physical separation between memory and processing units. Here, we present a novel closed-loop IMC circuit to compute real eigenvalues and eigenvectors of a target matrix allowing IMC-based acceleration of PCA. We benchmark its performance against a commercial GPU, achieving comparable accuracy and throughput while simultaneously securing ×10000 energy and ×100÷10000 area efficiency improvements. These results support IMC as a leading candidate architecture for energy-efficient ML accelerators
Development of Crosspoint Memory Arrays for Neuromorphic Computing
Full text linkMemristor-based hardware accelerators play a crucial role in achieving energy-efficient big data processing and artificial intelligence, overcoming the limitations of traditional von Neumann architectures. Resistive-switching memories (RRAMs) combine a simple two-terminal structure with the possibility of tuning the device conductance. This Chapter revolves around the topic of emerging memristor-related technologies, starting from their fabrication, through the characterization of single devices up to the development of proof-of-concept experiments in the field of in-memory computing, hardware accelerators, and brain-inspired architecture. Non-volatile devices are optimized for large-size crossbars where the devices’ conductance encodes mathematical coefficients of matrices. By exploiting Kirchhoff’s and Ohm’s law the matrix–vector-multiplication between the conductance matrix and a voltage vector is computed in one step. Eigenvalues/eigenvectors are experimentally calculated according to the power-iteration algorithm, with a fast convergence within about 10 iterations to the correct solution and Principal Component Analysis of the Wine and Iris datasets, showing up to 98% accuracy comparable to a floating-point implementation. Volatile memories instead present a spontaneous change of device conductance with a unique similarity to biological neuron behavior. This characteristic is exploited to demonstrate a simple fully-memristive architecture of five volatile RRAMs able to learn, store, and distinguish up to 10 different items with a memory capability of a few seconds. The architecture is thus tested in terms of robustness under many experimental conditions and it is compared with the real brain, disclosing interesting mechanisms which resemble the biological brain
Experimental verification and benchmark of in-memory principal component analysis by crosspoint arrays of resistive switching memory
No full textIn-memory computing (IMC) is gaining momentum
as the most promising candidate for the upcoming non-vonNeumann, machine learning-optimized computing paradigm. Its
intrinsic parallelism is well-suited to accelerate matrix-vector
multiplications (MVM), which prove challenging for traditional
architectures and are a fundamental operation in principal
component analysis (PCA), one of the most renowned algorithms for data classification. Here, we show an experimental
demonstration of a novel, IMC-based PCA algorithm by inmemory power iteration and deflation executed in a 4-kbit array
of resistive random-access memory (RRAM). Our algorithm
achieves 95.25% classification accuracy on the Wisconsin Diagnostic Breast Cancer dataset, matching closely results of a
floating-point machine while providing a 250× improvement in
energy efficiency
Time Complexity of In-Memory Solution of Linear Systems
Full text linkIn-memory computing (IMC) with cross-point resistive memory arrays has been shown to accelerate data-centric computations, such as the training and inference of deep neural networks, due to the high parallelism endowed by physical rules in the electrical circuits. By connecting cross-point arrays with negative feedback amplifiers, it is possible to solve linear algebraic problems, such as linear systems and matrix eigenvectors in just one step. Based on the theory of feedback circuits, we study the dynamics of the solution of linear systems within a memory array, showing that the time complexity of the solution is free of any direct dependence on the problem size {N} , rather it is governed by the minimal eigenvalue of an associated matrix of the coefficient matrix. We show that when the linear system is modeled by a covariance matrix, the time complexity is {O} (log {N} ) or {O} (1). In the case of sparse positive-definite linear systems, the time complexity is solely determined by the minimal eigenvalue of the coefficient matrix. These results demonstrate the high speed of the circuit for solving linear systems in a wide range of applications, thus supporting IMC as a strong candidate for future big data and machine learning accelerators
A Universal, Analog, In-Memory Computing Primitive for Linear Algebra Using Memristors
No full textThe increasing demand for data-intensive computing applications, such as artificial intelligence (AI) and more specifically machine learning (ML), raises the need for novel computing hardware architectures capable of massive parallelism in performing core algebraic operations. Among the new paradigms, in-memory computing (IMC) with analogue devices is attracting significant interest for its large-scale integration potential, together with unrivaled speed and energy performance. Here, we present a fully-analogue, universal primitive capable of executing linear algebra operations such as regression, generalized least-square minimization and linear system solution with and without preconditioning. We study the impact of the main circuit parameters on accuracy and bandwidth with analytical closed-form expressions and SPICE simulations. Scaling challenges due to parasitic resistance/capacitance and their impact on key parameters such as bandwidth and accuracy are discussed. Finally, a comparison with existing solvers belonging to the same IMC framework is made to assess advantages and disadvantages of the proposed circuit
An Ultrafast (< 200 ns) Sparse Solution Solver made by HfWOx/VOy Threshold Tunable Neurons
No full textEmerging Materials and Computing Paradigms for Temporal Signal Analysis
No full textIn the era of relentless data generation and dynamic information streams, the demand for efficient and robust temporal signal analysis has intensified across diverse domains such as healthcare, finance, and telecommunications. This perspective study explores the unfolding landscape of emerging materials and computing paradigms that are reshaping the way temporal signals are analyzed and interpreted. Traditional signal processing techniques often fall short when confronted with the intricacies of time-varying data, prompting the exploration of innovative approaches. The rise of emerging materials and devices empowers real-time analysis by processing temporal signals in situ, mitigating latency concerns. Through this perspective, the untapped potential of emerging materials and computing paradigms for temporal signal analysis is highlighted, offering valuable insights into both challenges and opportunities. Standing on the cusp of a new era in computing, understanding and harnessing these paradigms is pivotal for unraveling the complexities embedded within the temporal dimensions of data, propelling signal analysis into realms previously deemed inaccessible
Seizure detection via reservoir computing in MoS2-based charge trap memory devices
Full text link: Neurological disorders are a substantial global health burden, affecting millions of people worldwide. A key challenge in developing effective treatments and preventive measures is the realization of low-power wearable systems with early detection capabilities. Traditional strategies rely on machine learning algorithms, but their computational demands often exceed what miniaturized systems can provide. Neuromorphic computing, inspired by the human brain, demonstrated capabilities of on-chip computing with low power consumption. In this context, bidimensional (2D) semiconductors hold notable promise, thanks to their unique electronic properties, atomic-scale thickness, and scalability, making them ideal for low-power applications. This work presents a neuromorphic reservoir computing system exploiting MoS2-based charge trap memories (CTMs) for processing of electrophysiological signals. Real-time seizures detection is achieved, thanks to the nonlinear integration of local-field potential (LFP) recorded from in vitro rodent models of ictogenesis. The results support MoS2-based CTMs for low-power biomedical devices in clinical diagnosis and treatment of epilepsy
- …
