scholarly journals Cognitive Deficit of Deep Learning in Numerosity

2019 ◽  
Vol 33 ◽  
pp. 1303-1310
Author(s):  
Xiaolin Wu ◽  
Xi Zhang ◽  
Xiao Shu
Keyword(s):  
Deep Learning ◽  
Cognitive Deficit ◽  
Visual Representations ◽  
High Accuracy ◽  
Black Box ◽  
Cognitive Computing ◽  
Minimum Level ◽  
Test Bed ◽  
Abstract Notion

Subitizing, or the sense of small natural numbers, is an innate cognitive function of humans and primates; it responds to visual stimuli prior to the development of any symbolic skills, language or arithmetic. Given successes of deep learning (DL) in tasks of visual intelligence and given the primitivity of number sense, a tantalizing question is whether DL can comprehend numbers and perform subitizing. But somewhat disappointingly, extensive experiments of the type of cognitive psychology demonstrate that the examples-driven black box DL cannot see through superficial variations in visual representations and distill the abstract notion of natural number, a task that children perform with high accuracy and confidence. The failure is apparently due to the learning method not the CNN computational machinery itself. A recurrent neural network capable of subitizing does exist, which we construct by encoding a mechanism of mathematical morphology into the CNN convolutional kernels. Also, we investigate, using subitizing as a test bed, the ways to aid the black box DL by cognitive priors derived from human insight. Our findings are mixed and interesting, pointing to both cognitive deficit of pure DL, and some measured successes of boosting DL by predetermined cognitive implements. This case study of DL in cognitive computing is meaningful for visual numerosity represents a minimum level of human intelligence.

scholarly journals Deep Learning Accelerators: A Case Study

2020 ◽  
Author(s):  
Hamidreza Bolhasani ◽  
Somayyeh Jafarali Jassbi
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Performance Indicators ◽  
Learning Task ◽  
High Accuracy ◽  
The Other ◽  
Almost All ◽  
L1 And L2 ◽  
Accuracy Speed

Abstract In the recent years, deep learning has become one of the most important topics in computer science. Deep learning is a growing trend in the edge of technology and its applications are now seen in many aspects of our life such as object detection, speech recognition, natural language processing, etc. Currently, almost all major sciences and technologies are benefiting from the advantages of deep learning such as high accuracy, speed and flexibility. Therefore, any efforts for improving performance of related techniques is valuable. Deep learning accelerators are considered as hardware architecture, which are designed and optimized for increasing the speed, efficiency and accuracy of computers that are running deep learning algorithms. In this paper, after reviewing some backgrounds about deep learning, a well-known accelerator architecture named MAERI is investigated. By using an open source tool called MAESTRO, the performance of a deep learning task is measured and compared on two different data flow strategies: NLR and NVDLA. Measured performance indicators of novel optimized architecture, NVDLA shows higher L1 and L2 computation reuse and lower total runtime (cycles) in comparison to the other one.

scholarly journals Deep Learning Accelerators: A Case Study with MAESTRO

2020 ◽  
Author(s):  
Hamidreza Bolhasani ◽  
Somayyeh Jafarali Jassbi
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Performance Indicators ◽  
Learning Task ◽  
High Accuracy ◽  
Spatio Temporal ◽  
Almost All ◽  
L1 And L2 ◽  
Accuracy Speed

Abstract In recent years, deep learning has become one of the most important topics in computer sciences. Deep learning is a growing trend in the edge of technology and its applications are now seen in many aspects of our life such as object detection, speech recognition, natural language processing, etc. Currently, almost all major sciences and technologies are benefiting from the advantages of deep learning such as high accuracy, speed and flexibility. Therefore, any efforts in improving performance of related techniques is valuable. Deep learning accelerators are considered as hardware architecture, which are designed and optimized for increasing speed, efficiency and accuracy of computers that are running deep learning algorithms. In this paper, after reviewing some backgrounds on deep learning, a well-known accelerator architecture named MAERI (Multiply-Accumulate Engine with Reconfigurable interconnects) is investigated. Performance of a deep learning task is measured and compared in two different data flow strategies: NLR (No Local Reuse) and NVDLA (NVIDIA Deep Learning Accelerator), using an open source tool called MAESTRO (Modeling Accelerator Efficiency via Spatio-Temporal Resource Occupancy). Measured performance indicators of novel optimized architecture, NVDLA shows higher L1 and L2 computation reuse, and lower total runtime (cycles) in comparison to the other one.

scholarly journals Beyond Human: Deep Learning, Explainability and Representation

2020 ◽  
pp. 026327642096638
Author(s):  
M. Beatrice Fazi
Keyword(s):  
Artificial Intelligence ◽  
Feature Extraction ◽  
Deep Learning ◽  
Feature Learning ◽  
Human Mind ◽  
Black Box ◽  
Modes Of Representation ◽  
Computational Procedures ◽  
Algorithmic Thinking

This article addresses computational procedures that are no longer constrained by human modes of representation and considers how these procedures could be philosophically understood in terms of ‘algorithmic thought’. Research in deep learning is its case study. This artificial intelligence (AI) technique operates in computational ways that are often opaque. Such a black-box character demands rethinking the abstractive operations of deep learning. The article does so by entering debates about explainability in AI and assessing how technoscience and technoculture tackle the possibility to ‘re-present’ the algorithmic procedures of feature extraction and feature learning to the human mind. The article thus mobilises the notion of incommensurability (originally developed in the philosophy of science) to address explainability as a communicational and representational issue, which challenges phenomenological and existential modes of comparison between human and algorithmic ‘thinking’ operations.

scholarly journals Deep Learning Accelerators: A Case Study with MAESTRO

2020 ◽  
Author(s):  
Hamidreza Bolhasani ◽  
Somayyeh Jafarali Jassbi
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Performance Indicators ◽  
Learning Task ◽  
High Accuracy ◽  
Spatio Temporal ◽  
Almost All ◽  
L1 And L2 ◽  
Accuracy Speed

Abstract In recent years, deep learning has become one of the most important topics in computer sciences. Deep learning is a growing trend in the edge of technology and its applications are now seen in many aspects of our life such as object detection, speech recognition, natural language processing, etc. Currently, almost all major sciences and technologies are benefiting from the advantages of deep learning such as high accuracy, speed and flexibility. Therefore, any efforts in improving performance of related techniques is valuable. Deep learning accelerators are considered as hardware architecture, which are designed and optimized for increasing speed, efficiency and accuracy of computers that are running deep learning algorithms. In this paper, after reviewing some backgrounds on deep learning, a well-known accelerator architecture named MAERI (Multiply-Accumulate Engine with Reconfigurable interconnects) is investigated. Performance of a deep learning task is measured and compared in two different data flow strategies: NLR (No Local Reuse) and NVDLA (NVIDIA Deep Learning Accelerator), using an open source tool called MAESTRO (Modeling Accelerator Efficiency via Spatio-Temporal Resource Occupancy). Measured performance indicators of novel optimized architecture, NVDLA shows higher L1 and L2 computation reuse, and lower total runtime (cycles) in comparison to the other one.

scholarly journals Deep learning accelerators: a case study with MAESTRO

2020 ◽  
Vol 7 (1) ◽  
Author(s):  
Hamidreza Bolhasani ◽  
Somayyeh Jafarali Jassbi
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Performance Indicators ◽  
Learning Task ◽  
High Accuracy ◽  
Spatio Temporal ◽  
Almost All ◽  
L1 And L2 ◽  
Accuracy Speed

AbstractIn recent years, deep learning has become one of the most important topics in computer sciences. Deep learning is a growing trend in the edge of technology and its applications are now seen in many aspects of our life such as object detection, speech recognition, natural language processing, etc. Currently, almost all major sciences and technologies are benefiting from the advantages of deep learning such as high accuracy, speed and flexibility. Therefore, any efforts in improving performance of related techniques is valuable. Deep learning accelerators are considered as hardware architecture, which are designed and optimized for increasing speed, efficiency and accuracy of computers that are running deep learning algorithms. In this paper, after reviewing some backgrounds on deep learning, a well-known accelerator architecture named MAERI (Multiply-Accumulate Engine with Reconfigurable interconnects) is investigated. Performance of a deep learning task is measured and compared in two different data flow strategies: NLR (No Local Reuse) and NVDLA (NVIDIA Deep Learning Accelerator), using an open source tool called MAESTRO (Modeling Accelerator Efficiency via Spatio-Temporal Resource Occupancy). Measured performance indicators of novel optimized architecture, NVDLA shows higher L1 and L2 computation reuse, and lower total runtime (cycles) in comparison to the other one.

An Author as Literature. (Visual) Autofiction of Dorota Masłowska

2016 ◽  
Author(s):  
Anna Michalak
Keyword(s):  
New Media ◽  
Cultural Practices ◽  
Conceptual Art ◽  
Visual Representations ◽  
The Creation

Using the promotional meeting of Dorota Masłowska’s book "More than you can eat" (16 April 2015 in the Bar Studio, Warsaw), as a case study, the article examines the role author plays in it and try to show how the author itself can become the literature. As a result of the transformation of cultural practices associated with the new media, the author’s figure has gained much greater visibility which consequently changed its meaning. In the article, Masłowska’s artistic strategy is compared to visual autofiction in conceptual art and interpreted through the role of the performance and visual representations in the creation of the image or author’s brand.

Review of the Applications of Deep Learning in Bioinformatics

2021 ◽  
Vol 15 (8) ◽  
pp. 898-911
Author(s):  
Yongqing Zhang ◽  
Jianrong Yan ◽  
Siyu Chen ◽  
Meiqin Gong ◽  
Dongrui Gao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Drug Discovery ◽  
Biomedical Imaging ◽  
State Of The Art ◽  
Black Box ◽  
Medical Data ◽  
Biological Data ◽  
High Dimensional ◽  
Biological Research ◽  
Process Data

Rapid advances in biological research over recent years have significantly enriched biological and medical data resources. Deep learning-based techniques have been successfully utilized to process data in this field, and they have exhibited state-of-the-art performances even on high-dimensional, nonstructural, and black-box biological data. The aim of the current study is to provide an overview of the deep learning-based techniques used in biology and medicine and their state-of-the-art applications. In particular, we introduce the fundamentals of deep learning and then review the success of applying such methods to bioinformatics, biomedical imaging, biomedicine, and drug discovery. We also discuss the challenges and limitations of this field, and outline possible directions for further research.

scholarly journals Augmented Reality Maintenance Assistant Using YOLOv5

2021 ◽  
Vol 11 (11) ◽  
pp. 4758
Author(s):  
Ana Malta ◽  
Mateus Mendes ◽  
Torres Farinha
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Object Recognition ◽  
Augmented Reality ◽  
Real Time ◽  
Recognition System ◽  
High Accuracy ◽  
Video Streams ◽  
The Neural Network ◽  
Deep Learning Neural Network

Maintenance professionals and other technical staff regularly need to learn to identify new parts in car engines and other equipment. The present work proposes a model of a task assistant based on a deep learning neural network. A YOLOv5 network is used for recognizing some of the constituent parts of an automobile. A dataset of car engine images was created and eight car parts were marked in the images. Then, the neural network was trained to detect each part. The results show that YOLOv5s is able to successfully detect the parts in real time video streams, with high accuracy, thus being useful as an aid to train professionals learning to deal with new equipment using augmented reality. The architecture of an object recognition system using augmented reality glasses is also designed.

scholarly journals Detecting the pulmonary trunk in CT scout views using deep learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Aydin Demircioğlu ◽  
Magdalena Charis Stein ◽  
Moon-Sung Kim ◽  
Henrike Geske ◽  
Anton S. Quinsten ◽  
...  
Keyword(s):  
Deep Learning ◽  
Validation Cohort ◽  
High Accuracy ◽  
Pulmonary Trunk ◽  
Reference Standard ◽  
Bolus Tracking ◽  
Wilcoxon Rank Sum Test ◽  
Scout View ◽  
Axial Ct ◽  
Anterior Posterior

AbstractFor CT pulmonary angiograms, a scout view obtained in anterior–posterior projection is usually used for planning. For bolus tracking the radiographer manually locates a position in the CT scout view where the pulmonary trunk will be visible in an axial CT pre-scan. We automate the task of localizing the pulmonary trunk in CT scout views by deep learning methods. In 620 eligible CT scout views of 563 patients between March 2003 and February 2020 the region of the pulmonary trunk as well as an optimal slice (“reference standard”) for bolus tracking, in which the pulmonary trunk was clearly visible, was annotated and used to train a U-Net predicting the region of the pulmonary trunk in the CT scout view. The networks’ performance was subsequently evaluated on 239 CT scout views from 213 patients and was compared with the annotations of three radiographers. The network was able to localize the region of the pulmonary trunk with high accuracy, yielding an accuracy of 97.5% of localizing a slice in the region of the pulmonary trunk on the validation cohort. On average, the selected position had a distance of 5.3 mm from the reference standard. Compared to radiographers, using a non-inferiority test (one-sided, paired Wilcoxon rank-sum test) the network performed as well as each radiographer (P < 0.001 in all cases). Automated localization of the region of the pulmonary trunk in CT scout views is possible with high accuracy and is non-inferior to three radiographers.

Sign in / Sign up

Export Citation Format

Share Document