no code implementations • 10 Aug 2023 • Rickard Brännvall, Henrik Forsgren, Fredrik Sandin, Marcus Liwicki
It is demonstrated that the novel gating mechanism can capture long-term dependencies for a standard synthetic sequence learning task while significantly reducing computational costs such that execution time is reduced by half on CPU and by one-third under encryption.
1 code implementation • 5 Apr 2023 • Gustav Grund Pihlgren, Fredrik Sandin, Marcus Liwicki
The concept of image similarity is ambiguous, and images can be similar in one context and not in another.
1 code implementation • 8 Feb 2023 • Gustav Grund Pihlgren, Konstantina Nikolaidou, Prakash Chandra Chhipa, Nosheen Abid, Rajkumar Saini, Fredrik Sandin, Marcus Liwicki
Deep perceptual loss is a type of loss function in computer vision that aims to mimic human perception by using the deep features extracted from neural networks.
no code implementations • 24 Jan 2023 • Mattias Nilsson, Ton Juny Pina, Lyes Khacef, Foteini Liwicki, Elisabetta Chicca, Fredrik Sandin
With the expansion of AI-powered virtual assistants, there is a need for low-power keyword spotting systems providing a "wake-up" mechanism for subsequent computationally expensive speech recognition.
no code implementations • 20 Oct 2022 • Mattias Nilsson, Olov Schelén, Anders Lindgren, Ulf Bodin, Cristina Paniagua, Jerker Delsing, Fredrik Sandin
Based on this analysis, we propose a microservice-based framework for neuromorphic systems integration, consisting of a neuromorphic-system proxy, which provides virtualization and communication capabilities required in distributed systems of systems, in combination with a declarative programming approach offering engineering-process abstraction.
1 code implementation • 6 Jul 2022 • Oskar Sjögren, Gustav Grund Pihlgren, Fredrik Sandin, Marcus Liwicki
This work investigates the most common DPS metric, where deep features are compared by spatial position, along with metrics comparing the averaged and sorted deep features.
no code implementations • 11 Dec 2021 • Karl Löwenmark, Cees Taal, Stephan Schnabel, Marcus Liwicki, Fredrik Sandin
In the process industry, condition monitoring systems with automated fault diagnosis methods assist human experts and thereby improve maintenance efficiency, process sustainability, and workplace safety.
no code implementations • 10 Jun 2021 • Mattias Nilsson, Foteini Liwicki, Fredrik Sandin
Mixed-signal neuromorphic processors with brain-like organization and device physics offer an ultra-low-power alternative to the unsustainable developments of conventional deep learning and computing.
1 code implementation • 16 Mar 2020 • Gustav Grund Pihlgren, Fredrik Sandin, Marcus Liwicki
To evaluate this method we perform experiments on three standard publicly available datasets (LunarLander-v2, STL-10, and SVHN) and compare six different procedures for training image encoders (pixel-wise, perceptual similarity, and feature prediction losses; combined with two variations of image and feature encoding/decoding).
no code implementations • 12 Feb 2020 • Mattias Nilsson, Foteini Liwicki, Fredrik Sandin
Here, we investigate synaptic integration of spatiotemporal spike patterns with multiple dynamic synapses on point-neurons in the DYNAP-SE neuromorphic processor, which offers a complementary resource-efficient, albeit less flexible, approach to feature detection.
1 code implementation • 10 Jan 2020 • Gustav Grund Pihlgren, Fredrik Sandin, Marcus Liwicki
Autoencoders are trained to embed images from three different computer vision datasets using perceptual loss based on a pretrained model as well as pixel-wise loss.
no code implementations • 28 Jun 2019 • Fredrik Sandin, Mattias Nilsson
Furthermore, we present a network that mimics the auditory feature detection circuit of crickets and demonstrate how varying synapse weights, input noise and processor temperature affects the circuit.
no code implementations • 26 Mar 2019 • Jacob Nilsson, Fredrik Sandin, Jerker Delsing
Modern large-scale automation systems integrate thousands to hundreds of thousands of physical sensors and actuators.
no code implementations • 4 Feb 2019 • Sergio Martin-del-Campo, Fredrik Sandin, Daniel Strömbergsson
In this study, dictionaries are learned from gearbox vibrations in six different turbines, and the dictionaries are subsequently propagated over a few years of monitoring data when faults are known to occur.
no code implementations • 28 Nov 2016 • Fredrik Sandin, Sergio Martin-del-Campo
Sparse signal representations based on linear combinations of learned atoms have been used to obtain state-of-the-art results in several practical signal processing applications.
no code implementations • 12 Feb 2015 • Sergio Martin-del-Campo, Fredrik Sandin
In this paper, we investigate the possibility to automate the condition monitoring process by continuously learning a dictionary of optimized shift-invariant feature vectors using a well-known sparse approximation method.