A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
The Sloop System for Individual Animal Identification with Deep Learning
[article]
2020
arXiv
pre-print
We then show that priming with amplitude and deformation features requires very shallow networks to produce superior recognition results. ...
To do this, it adaptively represents and matches generic visual feature representations using sparse relevance feedback from experts and crowds. ...
"Pre-conditioning" with extracted features appears important to improve neural performance. ...
arXiv:2003.00559v1
fatcat:hemvrecmmredlfogbfoca2hn6q
Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data
[article]
2018
arXiv
pre-print
By utilizing novel deep learning methods for object detection and similarity comparisons, ecologists can extract animals from an image/video data and train deep learning classifiers to re-ID animal individuals ...
In this review, we describe a brief history of camera traps for re-ID, present a collection of computer vision feature engineering methodologies previously used for animal re-ID, provide an introduction ...
By considering modern deep learning approaches, ecologists can utilize improve accuracies without the requirement of handcoded feature extraction methods by training a neural network from large amounts ...
arXiv:1811.07749v1
fatcat:5mjlhtc3tfgvnnfsxb5b5z7ij4
Past, present and future approaches using computer vision for animal re‐identification from camera trap data
2019
Methods in Ecology and Evolution
By utilizing novel deep learning methods for object detection and similarity comparisons, ecologists can extract animals from an image/video data and train deep learning classifiers to re-ID animal individuals ...
For decades, ecologists with expertise in computer vision have successfully utilized feature engineering to extract meaningful features from camera trap images to improve the statistical rigor of individual ...
then extracting features (i.e. spots) using the SIFT algorithm. ...
doi:10.1111/2041-210x.13133
fatcat:wgfpo4mg6zbazhbzxfnp2dmkoq
Object-of-Interest Perception in a Reconfigurable Rolling-Crawling Robot
2022
Sensors
We train the locomotion mode recognition framework, named Pyramid Scene Parsing Network (PSPNet), with a self-collected dataset composed of two categories paths, unobstructed paths (e.g., floor) for rolling ...
and obstructed paths (e.g., with person, railing, stairs, static objects and wall) for crawling, respectively. ...
Neural network (PNN), Complementary Neural Network (CMTNN), and Space Invariant Artificial Neural Networks (SIANN) or Convolutional Neural Network (CNN) [21] . ...
doi:10.3390/s22145214
pmid:35890893
pmcid:PMC9315741
fatcat:njyegwwh7jfizhv52pz5aihkmy
Revealing Fine Structures of the Retinal Receptive Field by Deep Learning Networks
[article]
2020
arXiv
pre-print
Deep convolutional neural networks (CNNs) have demonstrated impressive performance on many visual tasks. Recently, they became useful models for the visual system in neuroscience. ...
Taken together, these results suggest that CNNs could be used to reveal structure components of neuronal circuits, and provide a powerful model for neural system identification. ...
a conv filter as a feature detector to extract useful information from input images [?] ...
arXiv:1811.02290v2
fatcat:v7wmejxsm5c4tcm7dkricljdri
Neural Activity Classification with Machine Learning Models Trained on Interspike Interval Time-Series Data
[article]
2021
bioRxiv
pre-print
Modern well-performing approaches to neural decoding are based on machine learning models such as decision tree ensembles and deep neural networks. ...
We demonstrate that an approach based on hand-crafted time-series feature engineering establishes a strong baseline performing on par with state-of-the-art deep learning based models for neural decoding ...
Such approaches include automated time series phenotyping implemented in the hctsa MATLAB package [19] and automated feature extraction in the tsfresh Python package [20] . ...
doi:10.1101/2021.03.24.436765
fatcat:ii4c2byzijcfbkm2kactrwodqa
A Retinotopic Spiking Neural Network System for Accurate Recognition of Moving Objects Using NeuCube and Dynamic Vision Sensors
2018
Frontiers in Computational Neuroscience
This paper introduces a new system for dynamic visual recognition that combines bio-inspired hardware with a brain-like spiking neural network. ...
The NeuCube architecture can be used to visualize the deep connectivity inside the network before, during, and after training and thereby allows for a better understanding of the learning processes. ...
ACKNOWLEDGMENTS The authors thank the reviewers for the useful comments and suggestions. ...
doi:10.3389/fncom.2018.00042
pmid:29946249
pmcid:PMC6006267
fatcat:rrz2o2qd4rcenlp4ylyocwcvea
Neurorobotics—A Thriving Community and a Promising Pathway Toward Intelligent Cognitive Robots
2018
Frontiers in Neurorobotics
In another example, a Deep Belief Neural Network was trained for object recognition and robot grasping (Hossain and Capi, 2016) . ...
In addition, deep neural networks have been used for robotic applications with promising results. ...
The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in ...
doi:10.3389/fnbot.2018.00042
pmid:30061820
pmcid:PMC6054919
fatcat:4ifhalmz2zeohndsjmulbceywi
Towards Detecting and Classifying Network Intrusion Traffic Using Deep Learning Frameworks
2019
Journal of Internet Services and Information Security
We apply and compare various state-of-the-art deep learning frameworks (e.g., Keras, TensorFlow, Theano, fast.ai, and PyTorch) in detecting network intrusion traffic and also in classifying common network ...
attack types using the recent CSE-CIC-IDS2018 dataset. ...
Any opinions, findings and conclusions, or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of the funding sources. ...
doi:10.22667/jisis.2019.11.30.001
dblp:journals/jisis/BasnetSJWD19
fatcat:xzzxwqpzjzhiffdsxi6237n3qi
PLANT SPECIE CLASSIFICATION USING SINUOSITY COEFFICIENTS OF LEAVES
2018
Image Analysis and Stereology
Conserving the plants may require the development of an automated system that will identify plants using leaf features such as shape, color, and texture. ...
The initial empirical experiments performed on the LeafSnap dataset on the usage of four sinuosity coefficients to characterize the leaf images using the Radial Basis Function Neural Network (RBF) and ...
Kalyoncu and Toygar (2015) proposed a method for plant recognition using leaf images based on the combination of new and well know feature extraction techniques and classification algorithms. ...
doi:10.5566/ias.1821
fatcat:qf3szmpe55dubltydw3jqkh7s4
Machine learning and applications in microbiology
2021
FEMS Microbiology Reviews
of mathematicians and computer scientists. ...
Our hope is to inspire microbiologists and other related researchers to join the emerging machine learning revolution. ...
Heavily regularised models, feature extraction or fine-tuning of pre-trained deep neural networks can help with these problems. Validation of predictions from ML is challenging. ...
doi:10.1093/femsre/fuab015
pmid:33724378
pmcid:PMC8498514
fatcat:v6sobinw45b3rdecprof4k62su
The stability of memories during brain remodeling: A perspective
2015
Communicative & Integrative Biology
O ne of the most important features of the nervous system is memory: the ability to represent and store experiences, in a manner that alters behavior and cognition at future times when the original stimulus ...
What can we learn from model species that exhibit both, regeneration and memory, with respect to robustness and stability requirements for long-term memories encoded in living tissues? ...
Pai, and Jennifer Hammelman for their helpful suggestions on the manuscript. This work was supported by the Templeton World Charity Foundation (TWCF0089/AB55) and the G. Harold and Leila Y. ...
doi:10.1080/19420889.2015.1073424
pmid:27066165
pmcid:PMC4802789
fatcat:dcxbwrciarbk3g5rxbylaq3siu
Neurorobots as a Means Toward Neuroethology and Explainable AI
2020
Frontiers in Neurorobotics
Understanding why deep neural networks and machine learning algorithms act as they do is a difficult endeavor. Neuroscientists are faced with similar problems. ...
In a similar way, neurorobotics can be used to explain how neural network activity leads to behavior. In real world settings, neurorobots have been shown to perform behaviors analogous to animals. ...
AUTHOR CONTRIBUTIONS All authors listed have made a substantial, direct and intellectual contribution to the work, and approved it for publication. ...
doi:10.3389/fnbot.2020.570308
pmid:33192435
pmcid:PMC7604467
fatcat:37v42xxymbfuznceh4gofmuawy
Tag Prediction at Flickr: a View from the Darkroom
[article]
2017
arXiv
pre-print
While deep convolutional neural networks have repeatedly demonstrated top performance on standard datasets for classification, there are a number of often overlooked but important considerations when deploying ...
Automated photo tagging has established itself as one of the most compelling applications of deep learning. ...
With deep neural networks being the de facto choice for image classification [21] , training models with thousands of classes and millions of parameters currently relies on access to large datasets of ...
arXiv:1612.01922v3
fatcat:y5ek65nfancwpfg3ddk4txc7wq
Species Classification for Neuroscience Literature Based on Span of Interest Using Sequence-to-Sequence Learning Model
2020
Frontiers in Human Neuroscience
We propose SpecExplorer project which is used to explore the knowledge associations of different species for brain and neuroscience. ...
Therefore, in addition to dictionary-based methods, we need to mine species using cognitive computing models that are more like the human reading process, and these methods can take advantage of the rich ...
Zhang and Zhou (2007) propose the BP-MLL with a fully-connected neural network and a pairwise ranking loss function. ...
doi:10.3389/fnhum.2020.00128
pmid:32372933
pmcid:PMC7187631
fatcat:6y2jop65fvgdpnhqt46tlfuuyi
« Previous
Showing results 1 — 15 out of 109 results