no code implementations • 23 Aug 2023 • Pedro Machado
This PhD research introduces three key contributions in the domain of object motion detection: Multi-Hierarchical Spiking Neural Network (MHSNN): A specialized four-layer Spiking Neural Network (SNN) architecture inspired by vertebrate retinas.
no code implementations • 22 Feb 2023 • Saminder Dhesi, Laura Fontes, Pedro Machado, Isibor Kennedy Ihianle, Farhad Fassihi Tash, David Ada Adama
Deep learning constitutes a pivotal component within the realm of machine learning, offering remarkable capabilities in tasks ranging from image recognition to natural language processing.
no code implementations • 6 Feb 2023 • Pavithra Koralalage, Ireoluwa Fakeye, Pedro Machado, Jason Smith, Isibor Kennedy Ihianle, Salisu Wada Yahaya, Andreas Oikonomou, Ahmad Lotfi
The experimental results showed that by using spike metrics and a range of weights, the desired output and the actual output of spiking neurons could be effectively optimised, leading to improved performance of SNNs.
no code implementations • 1 Feb 2023 • Zheqi Yu, Chao Zhang, Pedro Machado, Adnan Zahid, Tim. Fernandez-Hart, Muhammad A. Imran, Qammer H. Abbasi
The growing demand for optimal and low-power energy consumption paradigms for Internet of Things (IoT) devices has garnered significant attention due to their cost-effectiveness, simplicity, and intelligibility.
no code implementations • 15 Jan 2023 • Nicholas Murray-Hill, Laura Fontes, Pedro Machado, Isibor Kennedy Ihianle
Results: The proposed system successfully addresses the challenges of security, scalability, and efficiency in an IoT system used for surveillance and monitoring.
no code implementations • 21 Nov 2022 • Sandro Costa Magalhães, Filipe Neves Santos, Pedro Machado, António Paulo Moreira, Jorge Dias
The efficiency of the Tensor Processing Unit (TPU) is irrelevant and similar to NVIDIA Jetson TX2.
no code implementations • 25 Jul 2022 • Pedro Machado, T. M. McGinnity
We further demonstrate that, due to the high performance of the fingertips, a complex adaptive grasping algorithm is not required for grasping of everyday objects.
no code implementations • 13 Jul 2022 • Pedro Machado, Ivica Matic, Francisco de Lemos, Isibor Kennedy Ihianle, David Ada Adama
Modern-day life is driven by electronic devices connected to the internet.
no code implementations • 9 Jul 2022 • Isibor Kennedy Ihianle, Pedro Machado, Kayode Owa, David Ada Adama
Recent studies have shown that thermal comfort in a shared space is difficult to achieve due to individual preferences and the inability of occupants to reach a thermal compromise on temperature set points.
no code implementations • 6 Jul 2022 • Jakub Pomykala, Francisco de Lemos, Isibor Kennedy Ihianle, David Ada Adama, Pedro Machado
The use of artificial intelligence in the agricultural sector has been growing at a rapid rate to automate farming activities.
no code implementations • 6 Jul 2022 • Finlay McKinnon, David Ada Adama, Pedro Machado, Isibor Kennedy Ihianle
Due to the universal non-verbal natural communication approach that allows for effective communication between humans, gesture recognition technology has been steadily developing over the previous few decades.
no code implementations • 12 Dec 2021 • Pedro Machado, Joao Filipe Ferreira, Andreas Oikonomou, T. M. McGinnity
Vertebrate retinas are highly-efficient in processing trivial visual tasks such as detecting moving objects, yet a complex challenges for modern computers.
no code implementations • 9 Sep 2021 • Pedro Machado, Andreas Oikonomou, Joao Filipe Ferreira, T. M. McGinnity
The detection of moving objects is a trivial task performed by vertebrate retinas, yet a complex computer vision task.
no code implementations • 9 Sep 2021 • Wolfgang Bottcher, Pedro Machado, Nikesh Lama, T. M. McGinnity
Robots need to exploit high-quality information on grasped objects to interact with the physical environment.
no code implementations • 7 Nov 2020 • Samuel Brandenburg, Pedro Machado, Nikesh Lama, T. M. McGinnity
Over the last few years, the number of precision farming projects has increased specifically in harvesting robots and many of which have made continued progress from identifying crops to grasping the desired fruit or vegetable.
no code implementations • 18 Sep 2019 • Pedro Machado, Georgina Cosma, T. M. McGinnity
Biological image processing is performed by complex neural networks composed of thousands of neurons interconnected via thousands of synapses, some of which are excitatory and others inhibitory.