Related papers: A Model-Free Method to Quantify Memory Utilization…
Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…
Many studies have explored brain signals during the performance of a memory task to predict later remembered items. However, prediction methods are still poorly used in real life and are not practical due to the use of…
There is unprecedented development in machine learning, exemplified by recent large language models and world simulators, which are artificial neural networks running on digital computers. However, they still cannot parallel human brains in…
By informing the onset of the degradation process, health status evaluation serves as a significant preliminary step for reliable remaining useful life (RUL) estimation of complex equipment. This paper proposes a novel temporal dynamics…
Since its inception, the neural estimation of mutual information (MI) has demonstrated the empirical success of modeling expected dependency between high-dimensional random variables. However, MI is an aggregate statistic and cannot be used…
As data-intensive applications increasingly strain conventional computing systems, processing-in-memory (PIM) has emerged as a promising paradigm to alleviate the memory wall by minimizing data transfer between memory and processing units.…
The rapid advancement of deep neural networks has significantly improved various tasks, such as image and speech recognition. However, as the complexity of these models increases, so does the computational cost and the number of parameters,…
Dissipative cognitive architectures maintain computation through continuous energy expenditure, where units that exhaust their energy are stochastically replaced with fresh random state. This creates a fundamental challenge: how can…
We study distributed algorithms implemented in a simplified biologically inspired model for stochastic spiking neural networks. We focus on tradeoffs between computation time and network complexity, along with the role of randomness in…
Inertial Measurement Unit (IMU)-based Human Activity Recognition (HAR) aims to interpret and classify user behaviors from temporal motion signals. Recently, deep learning frameworks have advanced this task by learning and extracting…
The Memory stress (Mess) framework provides a unified view of the memory system benchmarking, simulation and application profiling. The Mess benchmark provides a holistic and detailed memory system characterization. It is based on hundreds…
Processing-in-memory (PIM) turns out to be a promising solution to breakthrough the memory wall and the power wall. While prior PIM designs yield successful implementation of bitwise Boolean logic operations locally in memory, it is…
Quantization is essential for Neural Network (NN) compression, reducing model size and computational demands by using lower bit-width data types, though aggressive reduction often hampers accuracy. Mixed Precision (MP) mitigates this…
This paper summarizes the ideas and key concepts in MISE (Memory Interference-induced Slowdown Estimation), which was published in HPCA 2013 [97], and examines the work's significance and future potential. Applications running concurrently…
Quantum computing and neural networks show great promise for the future of information processing. In this paper we study a quantum reservoir computer (QRC), a framework harnessing quantum dynamics and designed for fast and efficient…
Reservoir computing is a subfield of machine learning in which a complex system, or 'reservoir,' uses complex internal dynamics to non-linearly project an input into a higher-dimensional space. A single trainable output layer then inspects…
Task based neuroimaging tools for the study of cognitive neuroscience provide insight into understanding how the brain responds to increasing cognitive demand. Theoretical models of neural-cognitive relationships have been developed based…
Here we present our Python toolbox "MR. Estimator" to reliably estimate the intrinsic timescale from electrophysiologal recordings of heavily subsampled systems. Originally intended for the analysis of time series from neuronal spiking…
Active systems across scales, ranging from molecular machines to human crowds, are usually modeled as assemblies of self-propelled particles driven by internally generated forces. However, these models often assume memoryless dynamics and…
Mathematical approaches from dynamical systems theory are used in a range of fields. This includes biology where they are used to describe processes such as protein-protein interaction and gene regulatory networks. As such networks increase…