Search Results for author: Pawel Herman

Found 16 papers, 2 papers with code

Benchmarking Hebbian learning rules for associative memory

no code implementations30 Dec 2023 Anders Lansner, Naresh B Ravichandran, Pawel Herman

In this paper we characterize these different aspects of associative memory performance and benchmark six different learning rules on storage capacity and prototype extraction.

Benchmarking

Sourcing Investment Targets for Venture and Growth Capital Using Multivariate Time Series Transformer

no code implementations28 Sep 2023 Lele Cao, Gustaf Halvardsson, Andrew McCornack, Vilhelm von Ehrenheim, Pawel Herman

This paper addresses the growing application of data-driven approaches within the Private Equity (PE) industry, particularly in sourcing investment targets (i. e., companies) for Venture Capital (VC) and Growth Capital (GC).

Data Augmentation Decision Making +2

Spiking neural networks with Hebbian plasticity for unsupervised representation learning

no code implementations5 May 2023 Naresh Ravichandran, Anders Lansner, Pawel Herman

We introduce a novel spiking neural network model for learning distributed internal representations from data in an unsupervised procedure.

Representation Learning

Hebbian fast plasticity and working memory

no code implementations13 Apr 2023 Anders Lansner, Florian Fiebig, Pawel Herman

Theories and models of working memory (WM) were at least since the mid-1990s dominated by the persistent activity hypothesis.

Metaheuristic conditional neural network for harvesting skyrmionic metastable states

no code implementations6 Mar 2023 Qichen Xu, I. P. Miranda, Manuel Pereiro, Filipp N. Rybakov, Danny Thonig, Erik Sjöqvist, Pavel Bessarab, Anders Bergman, Olle Eriksson, Pawel Herman, Anna Delin

To demonstrate how this method works, we identify and analyze spin textures with topological charge $Q$ ranging from 1 to $-13$ (where antiskyrmions have $Q<0$) in the Pd/Fe/Ir(111) system, which we model using a classical atomistic spin Hamiltonian based on parameters computed from density functional theory.

Genetic-tunneling driven energy optimizer for spin systems

1 code implementation31 Dec 2022 Qichen Xu, Zhuanglin Shen, Manuel Pereiro, Pawel Herman, Olle Eriksson, Anna Delin

A long-standing and difficult problem in, e. g., condensed matter physics is how to find the ground state of a complex many-body system where the potential energy surface has a large number of local minima.

Brain-like combination of feedforward and recurrent network components achieves prototype extraction and robust pattern recognition

no code implementations30 Jun 2022 Naresh Balaji Ravichandran, Anders Lansner, Pawel Herman

We approach this problem by combining a recurrent attractor network with a feedforward network that learns distributed representations using an unsupervised Hebbian-Bayesian learning rule.

A Long Short-term Memory Based Recurrent Neural Network for Interventional MRI Reconstruction

no code implementations28 Mar 2022 Ruiyang Zhao, Zhao He, Tao Wang, Suhao Qiu, Pawel Herman, Yanle Hu, Chencheng Zhang, Dinggang Shen, Bomin Sun, Guang-Zhong Yang, Yuan Feng

Here we proposed a convolutional long short-term memory (Conv-LSTM) based recurrent neural network (RNN), or ConvLR, to reconstruct interventional images with golden-angle radial sampling.

MRI Reconstruction

Semi-supervised learning with Bayesian Confidence Propagation Neural Network

no code implementations29 Jun 2021 Naresh Balaji Ravichandran, Anders Lansner, Pawel Herman

Learning internal representations from data using no or few labels is useful for machine learning research, as it allows using massive amounts of unlabeled data.

Brain-like approaches to unsupervised learning of hidden representations - a comparative study

no code implementations1 Jan 2021 Naresh Balaji, Anders Lansner, Pawel Herman

Unsupervised learning of hidden representations has been one of the most vibrant research directions in machine learning in recent years.

BIG-bench Machine Learning

Automatic Particle Trajectory Classification in Plasma Simulations

no code implementations11 Oct 2020 Stefano Markidis, Ivy Peng, Artur Podobas, Itthinat Jongsuebchoke, Gabriel Bengtsson, Pawel Herman

Our overall goal is to provide a general workflow for exploring particle trajectory space and automatically classifying particle trajectories from plasma simulations in an unsupervised manner.

Classification Clustering +1

Brain-like approaches to unsupervised learning of hidden representations -- a comparative study

no code implementations6 May 2020 Naresh Balaji Ravichandran, Anders Lansner, Pawel Herman

Unsupervised learning of hidden representations has been one of the most vibrant research directions in machine learning in recent years.

BIG-bench Machine Learning

Learning representations in Bayesian Confidence Propagation neural networks

no code implementations27 Mar 2020 Naresh Balaji Ravichandran, Anders Lansner, Pawel Herman

Unsupervised learning of hierarchical representations has been one of the most vibrant research directions in deep learning during recent years.

Characterizing Deep-Learning I/O Workloads in TensorFlow

no code implementations6 Oct 2018 Steven W. D. Chien, Stefano Markidis, Chaitanya Prasad Sishtla, Luis Santos, Pawel Herman, Sai Narasimhamurthy, Erwin Laure

To measure TensorFlow I/O performance, we first design a micro-benchmark to measure TensorFlow reads, and then use a TensorFlow mini-application based on AlexNet to measure the performance cost of I/O and checkpointing in TensorFlow.

Distributed, Parallel, and Cluster Computing

Cannot find the paper you are looking for? You can Submit a new open access paper.