NT
N. Tömen
Authored
1 records found
Top-down networks
A coarse-to-fine reimagination of CNNs
Biological vision adopts a coarse-to-fine information processing pathway, from initial visual detection and binding of salient features of a visual scene, to the enhanced and preferential processing given relevant stimuli. On the contrary, CNNs employ a fine-to-coarse processing,
...
Contributed
19 records found
Benchmarking Neural Decoders
Benchmarking of Hardware-efficient Real-time Neural Decoding in Brain-computer Interfaces
Designing processors for implantable closed-loop neuromodulation systems presents a formidable challenge owing to the constrained operational environment, which requires low latency and high energy efficacy. Previous benchmarks have provided limited insights into power consumption
...
Identification of subjects from reconstructed images
Identification of individual subjects based on image reconstructions generated from fMRI brain scans
Reconstructing seen images from functional magnetic resonance imaging (fMRI) brain scans has been a growing topic of interest in the field of neuroscience, fostered by innovation in machine learning and AI. This paper investigates the possible presence of personal features allowi
...
Denoising task fMRI data for image reconstructions
Denoising of Functional Magnetic Resonance Imaging (fMRI) Data for Improved Visual Stimulus Reconstruction using Machine Learning
This study aims to investigate the impact of various denoising algorithms on the quality of visual stimulus reconstructions based on functional magnetic resonance imaging (fMRI) data. While fMRI provides a valuable, noninvasive method for assessing brain activity, the reliability
...
As technology advances, automated systems become more autonomous which leads to a higher interdependence between machine and human. Much research has been done about trust between humans and trust of humans regarding machines. An interesting question that remains is how the behav
...
BladeSynth
Damage Detection and Assessment in Aircraft Engines with Synthetic Data
Deep learning has been widely implemented in industrial inspection, such as damage detection from images. However, training deep networks requires massive data, which is hard to collect and laborious to annotate, especially in the aviation scenario of aircraft engines. To allevia
...
Learning Reduced-Order Mappings between Functions
An Investigation of Suitable Inputs and Outputs
Data-driven approaches are a promising new addition to the list of available strategies for solving Partial Differential Equations (PDEs). One such approach, the Principal Component Analysis-based Neural Network PDE solver, can be used to learn a mapping between two function spac
...
Learning Reduced Order Mappings of Navier-Stokes
An Investigation of Generalization on the Viscosity Parameter
Solving Partial Differential Equations (PDEs) in engineering such as Navier-Stokes is incredibly computationally expensive and complex. Without analytical solutions, numerical solutions can take ages to simulate at great expense. In order to reduce this cost, neural networks may
...
Data Driven Approximations Of PDEs
On Robustness of Reduced Order Mappings between Function Spaces Against Noise
This paper presents a comprehensive exploration of a novel method combining Principal Component Analysis (PCA) and Neural Networks (NN) to efficiently solve Partial Differential Equations (PDEs), a fundamental challenge in modeling a wide range of real-world phenomena. Our resear
...
The role of membrane time constant in the training of spiking neural networks
Improving accuracy by per-neuron learning
Spiking neural networks (SNNs) aim to utilize mechanisms from biological neurons to bridge the computational and efficiency gaps between the human brain and machine learning systems. The widely used Leaky-Integrate-and-Fire (LIF) neuron model accumulates input spikes into an expo
...
Impact of time-discretization on the efficiency of continuous time Spiking Neural Networks
The effects of the time step size on the accuracy, sparsity and latency of the SNN
The increasing computational costs of training deep learning models have drawn more and more attention towards more power-efficient alternatives such as spiking neural networks (SNNs). SNNs are an artificial neural network that mimics the brain’s way of processing information. Th
...
Impact of time-discretization on the efficiency of continuous time Spiking Neural Networks
The effects of the time step size on the accuracy, sparsity and latency of the SNN
The increasing computational costs of training deep learning models have drawn more and more attention towards more power-efficient alternatives such as spiking neural networks (SNNs). SNNs are an artificial neural network that mimics the brain’s way of processing information. Th
...
Adapting unconstrained spiking neural networks to explore the effects of time discretization on network properties
Correlation between step size and accuracy for real world task
Spiking Neural Networks (SNN) represent a distinct class of neural network models that incorporate an additional temporal dimension. Neurons within SNN operate according to the Leaky Integrate-and-Fire principle, governed by ordinary differential equations. Inter-layer neuronal c
...
Adapting unconstrained spiking neural networks to explore the effects of time discretization on network properties
Correlation between step size and accuracy for real world task
Spiking Neural Networks (SNN) represent a distinct class of neural network models that incorporate an additional temporal dimension. Neurons within SNN operate according to the Leaky Integrate-and-Fire principle, governed by ordinary differential equations. Inter-layer neuronal c
...
Unsupervised optical flow estimation of event cameras
The influence of training sets on model performance
Event cameras are cameras that capture events asynchronously based on changes in lighting. They offer multiple benifits, but pose challenges in computer vision due to their asynchronous nature and hard to capture ground truth values to compare against. This paper shows the effect
...
Unsupervised optical flow estimation of event cameras
The influence of training sets on model performance
Event cameras are cameras that capture events asynchronously based on changes in lighting. They offer multiple benifits, but pose challenges in computer vision due to their asynchronous nature and hard to capture ground truth values to compare against. This paper shows the effect
...
Adapting unconstrained spiking neural networks to explore the effects of time discretization on network properties
The effects of time-discretization on spike-based backpropagation as opposed to membrane-potential backpropagation
The promise of Artificial Neural Networks has lead to their immense usage intertwined with concerns over energy consumption. This has led to development of alternatives, such as Spiking Neural Networks (SNNs), which allows their implementation on neuromorphic hardware. In effect,
...
Optical Flow Estimation Using Event-Based Cameras
Improving Optical Flow Estimation Accuracy Using Space-Aware De-Flickering
Event cameras are novel sensors whose high temporal resolution and bandwidth motivate their use for the optical flow estimation problem. However, the properties of event cameras also introduce a vulnerability to flickering. Flickering hurts the perceptibility of motion by overwhe
...
Backpropagating in time-discretized multi-spike spiking neural networks
How are the training accuracy and training speed (in epochs and time) of a spiking neural network affected when numerically integrating with the forward-Euler and Parker-Sochacki methods?
Spiking neural networks have gained traction as both a tool for neuroscience research and a new frontier in machine learning. A plethora of neuroscience literature exists exploring the realistic simulation of neurons, with complex models re- quiring the formulation and integratio
...
Backpropagating in time-discretized multi-spike spiking neural networks
How are the training accuracy and training speed (in epochs and time) of a spiking neural network affected when numerically integrating with the forward-Euler and Parker-Sochacki methods?
Spiking neural networks have gained traction as both a tool for neuroscience research and a new frontier in machine learning. A plethora of neuroscience literature exists exploring the realistic simulation of neurons, with complex models re- quiring the formulation and integratio
...