scholarly journals Using deep neural networks to evaluate object vision tasks in rats

2021 ◽  
Vol 17 (3) ◽  
pp. e1008714
Author(s):  
Kasper Vinken ◽  
Hans Op de Beeck
Keyword(s):  
Neural Networks ◽  
Information Processing ◽  
Object Recognition ◽  
Deep Neural Networks ◽  
Convincing Evidence ◽  
Complex Object ◽  
Visual Neuroscience ◽  
Wide Range ◽  
Invariant Object Recognition ◽  
Properties Of Information

In the last two decades rodents have been on the rise as a dominant model for visual neuroscience. This is particularly true for earlier levels of information processing, but a number of studies have suggested that also higher levels of processing such as invariant object recognition occur in rodents. Here we provide a quantitative and comprehensive assessment of this claim by comparing a wide range of rodent behavioral and neural data with convolutional deep neural networks. These networks have been shown to capture hallmark properties of information processing in primates through a succession of convolutional and fully connected layers. We find that performance rodent object vision tasks can be captured using low to mid-level convolutional layers only, without any convincing evidence for the need of higher layers known to simulate complex object recognition in primates. Our approach also reveals surprising insights on assumptions made before, for example, that the best performing animals would be the ones using the most abstract representations–which we show to likely be incorrect. Our findings suggest a road ahead for further studies aiming at quantifying and establishing the richness of representations underlying information processing in animal models at large.

scholarly journals Deep Neural Networks Point to Mid-level Complexity of Rodent Object Vision

2020 ◽  
Author(s):  
Kasper Vinken ◽  
Hans Op de Beeck
Keyword(s):  
Neural Networks ◽  
Information Processing ◽  
Object Recognition ◽  
Deep Neural Networks ◽  
Convincing Evidence ◽  
Complex Object ◽  
Visual Neuroscience ◽  
Wide Range ◽  
Invariant Object Recognition ◽  
Fully Connected

AbstractIn the last two decades rodents have been on the rise as a dominant model for visual neuroscience. This is particularly true for earlier levels of information processing, but high-profile papers have suggested that also higher levels of processing such as invariant object recognition occur in rodents. Here we provide a quantitative and comprehensive assessment of this claim by comparing a wide range of rodent behavioral and neural data with convolutional deep neural networks. These networks have been shown to capture the richness of information processing in primates through a succession of convolutional and fully connected layers. We find that rodent object vision can be captured using low to mid-level convolutional layers only, without any convincing evidence for the need of higher layers known to simulate complex object recognition in primates. Our approach also reveals surprising insights on assumptions made before, for example, that the best performing animals would be the ones using the most complex representations – which we show to likely be incorrect. Our findings suggest a road ahead for further studies aiming at quantifying and establishing the richness of representations underlying information processing in animal models at large.

scholarly journals Marmoset invariant object recognition behavior mirrors that of humans and macaques at fine scale

2020 ◽  
Author(s):  
Alexander J.E. Kell ◽  
Sophie L. Bokor ◽  
You-Nah Jeon ◽  
Tahereh Toosi ◽  
Elias B. Issa
Keyword(s):  
Object Recognition ◽  
Model Organism ◽  
High Standard ◽  
Visual Object ◽  
Visual Object Recognition ◽  
Visual Neuroscience ◽  
Brain Functions ◽  
Invariant Object Recognition ◽  
Small Model ◽  
High Level

The marmoset—a small monkey with a flat cortex—offers powerful techniques for studying neural circuits in a primate. However, it remains unclear whether brain functions typically studied in larger primates can be studied in the marmoset. Here, we asked whether the 300-gram marmosets’ perceptual and cognitive repertoire approaches human levels or is instead closer to rodents’. Using high-level visual object recognition as a testbed, we found that on the same task marmosets substantially outperformed rats and generalized far more robustly across images, all while performing ∼1000 trials/day. We then compared marmosets against the high standard of human behavior. Across the same 400 images, marmosets’ image-by-image recognition behavior was strikingly human-like—essentially as human-like as macaques’. These results demonstrate that marmosets have been substantially underestimated and that high-level abilities have been conserved across simian primates. Consequently, marmosets are a potent small model organism for visual neuroscience, and perhaps beyond.

Deep neural networks with Elastic Rectified Linear Units for object recognition

2018 ◽  
Vol 275 ◽  
pp. 1132-1139 ◽  
Author(s):  
Xiaoheng Jiang ◽  
Yanwei Pang ◽  
Xuelong Li ◽  
Jing Pan ◽  
Yinghong Xie
Keyword(s):  
Neural Networks ◽  
Object Recognition ◽  
Deep Neural Networks

scholarly journals COSMO: Computing with Stochastic Numbers in Memory

2022 ◽  
Vol 18 (2) ◽  
pp. 1-25
Author(s):  
Saransh Gupta ◽  
Mohsen Imani ◽  
Joonseop Sim ◽  
Andrew Huang ◽  
Fan Wu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Energy Efficient ◽  
Deep Neural Networks ◽  
Parallel Architecture ◽  
Low Energy ◽  
Stochastic Computing ◽  
Wide Range ◽  
Low Energy Consumption ◽  
Sc Addition

Stochastic computing (SC) reduces the complexity of computation by representing numbers with long streams of independent bits. However, increasing performance in SC comes with either an increase in area or a loss in accuracy. Processing in memory (PIM) computes data in-place while having high memory density and supporting bit-parallel operations with low energy consumption. In this article, we propose COSMO, an architecture for co mputing with s tochastic numbers in me mo ry, which enables SC in memory. The proposed architecture is general and can be used for a wide range of applications. It is a highly dense and parallel architecture that supports most SC encodings and operations in memory. It maximizes the performance and energy efficiency of SC by introducing several innovations: (i) in-memory parallel stochastic number generation, (ii) efficient implication-based logic in memory, (iii) novel memory bit line segmenting, (iv) a new memory-compatible SC addition operation, and (v) enabling flexible block allocation. To show the generality and efficiency of our stochastic architecture, we implement image processing, deep neural networks (DNNs), and hyperdimensional (HD) computing on the proposed hardware. Our evaluations show that running DNN inference on COSMO is 141× faster and 80× more energy efficient as compared to GPU.

scholarly journals “A Learning Method for Object Detection from Low Resolution Image”

2020 ◽  
Vol 8 (6) ◽  
pp. 3992-3995
Keyword(s):  
Neural Networks ◽  
Object Recognition ◽  
Object Detection ◽  
Deep Neural Networks ◽  
Learning Method ◽  
Low Resolution ◽  
Resolution Image ◽  
Overall Performance ◽  
Network Object

Object recognition the use deep neural networks has been most typically used in real applications. We propose a framework for identifying items in pics of very low decision through collaborative studying of two deep neural networks. It includes photo enhancement network object popularity networks. The picture correction community seeks to decorate images of much lower decision faster and more informative images with the usages of collaborative gaining knowledge of indicatores from object recognition networks. Object popularity networks actively participate in the mastering of photograph enhancement networks, with skilled weights for photographs of excessive resolution. It uses output from photograph enhancement networks as augmented studying recordes to reinforce the overall performance of its identity on a very low decision object. We esablished that the proposed method can improve photograph reconstruction and classification overall performance

scholarly journals Really natural adversarial examples

2021 ◽  
Author(s):  
Anibal Pedraza ◽  
Oscar Deniz ◽  
Gloria Bueno
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Object Recognition ◽  
Image Quality ◽  
Real World ◽  
Deep Neural Networks ◽  
Distance Metrics ◽  
The Real ◽  
Adversarial Examples ◽  
General Object

AbstractThe phenomenon of Adversarial Examples has become one of the most intriguing topics associated to deep learning. The so-called adversarial attacks have the ability to fool deep neural networks with inappreciable perturbations. While the effect is striking, it has been suggested that such carefully selected injected noise does not necessarily appear in real-world scenarios. In contrast to this, some authors have looked for ways to generate adversarial noise in physical scenarios (traffic signs, shirts, etc.), thus showing that attackers can indeed fool the networks. In this paper we go beyond that and show that adversarial examples also appear in the real-world without any attacker or maliciously selected noise involved. We show this by using images from tasks related to microscopy and also general object recognition with the well-known ImageNet dataset. A comparison between these natural and the artificially generated adversarial examples is performed using distance metrics and image quality metrics. We also show that the natural adversarial examples are in fact at a higher distance from the originals that in the case of artificially generated adversarial examples.

scholarly journals Distinguishing between recent balancing selection and incomplete sweep using deep neural networks

2020 ◽  
Author(s):  
Ulas Isildak ◽  
Alessandro Stella ◽  
Matteo Fumagalli
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Balancing Selection ◽  
False Positive Rate ◽  
Genomic Data ◽  
Training Data ◽  
Functional Changes ◽  
Wide Range ◽  
Recent Selection

1AbstractBalancing selection is an important adaptive mechanism underpinning a wide range of phenotypes. Despite its relevance, the detection of recent balancing selection from genomic data is challenging as its signatures are qualitatively similar to those left by ongoing positive selection. In this study we developed and implemented two deep neural networks and tested their performance to predict loci under recent selection, either due to balancing selection or incomplete sweep, from population genomic data. Specifically, we generated forward-intime simulations to train and test an artificial neural network (ANN) and a convolutional neural network (CNN). ANN received as input multiple summary statistics calculated on the locus of interest, while CNN was applied directly on the matrix of haplotypes. We found that both architectures have high accuracy to identify loci under recent selection. CNN generally outperformed ANN to distinguish between signals of balancing selection and incomplete sweep and was less affected by incorrect training data. We deployed both trained networks on neutral genomic regions in European populations and demonstrated a lower false positive rate for CNN than ANN. We finally deployed CNN within the MEFV gene region and identified several common variants predicted to be under incomplete sweep in a European population. Notably, two of these variants are functional changes and could modulate susceptibility to Familial Mediterranean Fever, possibly as a consequence of past adaptation to pathogens. In conclusion, deep neural networks were able to characterise signals of selection on intermediate-frequency variants, an analysis currently inaccessible by commonly used strategies.

Sign in / Sign up

Export Citation Format

Share Document