Learning About the World by Learning About Images

2021 ◽  
pp. 096372142199033
Author(s):  
Katherine R. Storrs ◽  
Roland W. Fleming
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Visual Processing ◽  
Visual Experience ◽  
Natural Images ◽  
Sensory Coding ◽  
The World ◽  
Unsupervised Deep Learning ◽  
Statistical Regularities ◽  
Sensory Encoding

One of the deepest insights in neuroscience is that sensory encoding should take advantage of statistical regularities. Humans’ visual experience contains many redundancies: Scenes mostly stay the same from moment to moment, and nearby image locations usually have similar colors. A visual system that knows which regularities shape natural images can exploit them to encode scenes compactly or guess what will happen next. Although these principles have been appreciated for more than 60 years, until recently it has been possible to convert them into explicit models only for the earliest stages of visual processing. But recent advances in unsupervised deep learning have changed that. Neural networks can be taught to compress images or make predictions in space or time. In the process, they learn the statistical regularities that structure images, which in turn often reflect physical objects and processes in the outside world. The astonishing accomplishments of unsupervised deep learning reaffirm the importance of learning statistical regularities for sensory coding and provide a coherent framework for how knowledge of the outside world gets into visual cortex.

scholarly journals Deep Malaria Parasite Detection in Thin Blood Smear Microscopic Images

2021 ◽  
Vol 11 (5) ◽  
pp. 2284
Author(s):  
Asma Maqsood ◽  
Muhammad Shahid Farid ◽  
Muhammad Hassan Khan ◽  
Marcin Grzegorzek
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Red Blood Cells ◽  
Convolutional Neural Networks ◽  
Blood Cells ◽  
Superior Performance ◽  
Learning Models ◽  
Infected Female ◽  
The World ◽  
Augmentation Techniques

Malaria is a disease activated by a type of microscopic parasite transmitted from infected female mosquito bites to humans. Malaria is a fatal disease that is endemic in many regions of the world. Quick diagnosis of this disease will be very valuable for patients, as traditional methods require tedious work for its detection. Recently, some automated methods have been proposed that exploit hand-crafted feature extraction techniques however, their accuracies are not reliable. Deep learning approaches modernize the world with their superior performance. Convolutional Neural Networks (CNN) are vastly scalable for image classification tasks that extract features through hidden layers of the model without any handcrafting. The detection of malaria-infected red blood cells from segmented microscopic blood images using convolutional neural networks can assist in quick diagnosis, and this will be useful for regions with fewer healthcare experts. The contributions of this paper are two-fold. First, we evaluate the performance of different existing deep learning models for efficient malaria detection. Second, we propose a customized CNN model that outperforms all observed deep learning models. It exploits the bilateral filtering and image augmentation techniques for highlighting features of red blood cells before training the model. Due to image augmentation techniques, the customized CNN model is generalized and avoids over-fitting. All experimental evaluations are performed on the benchmark NIH Malaria Dataset, and the results reveal that the proposed algorithm is 96.82% accurate in detecting malaria from the microscopic blood smears.

A Review of Recent Deep Learning Models in COVID-19 Diagnosis

2021 ◽  
Vol 6 (5) ◽  
pp. 10-15
Author(s):  
Ela Bhattacharya ◽  
D. Bhattacharya
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Test Results ◽  
Learning Models ◽  
Future Directions ◽  
Human Contact ◽  
The World ◽  
Short Span

COVID-19 has emerged as the latest worrisome pandemic, which is reported to have its outbreak in Wuhan, China. The infection spreads by means of human contact, as a result, it has caused massive infections across 200 countries around the world. Artificial intelligence has likewise contributed to managing the COVID-19 pandemic in various aspects within a short span of time. Deep Neural Networks that are explored in this paper have contributed to the detection of COVID-19 from imaging sources. The datasets, pre-processing, segmentation, feature extraction, classification and test results which can be useful for discovering future directions in the domain of automatic diagnosis of the disease, utilizing artificial intelligence-based frameworks, have been investigated in this paper.

The Exploration of Autonomous Vehicles

2022 ◽  
pp. 930-944
Author(s):  
Anthony J. Gephardt ◽  
Elizabeth Baoying Wang
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Intelligent Agents ◽  
Autonomous Vehicles ◽  
Learning Processes ◽  
Artificial Intelligent ◽  
The World ◽  
History Of ◽  
The Creation

This chapter explores the world of autonomous vehicles. Starting from the beginning, it covers the history of the automobile dating back to 1769. It explains how the first production automobile came about in 1885. The chapter dives into the history of auto safety, ranging from seatbelts to full-on autonomous features. One of the main focuses is the creation and implementation of artificial intelligent (AI), neural networks, intelligent agents, and deep Learning Processes. Combining the hardware on the vehicle with the intelligence of AI creates what we know as autonomous vehicles today.

Bio-Medical Image Processing

2020 ◽  
pp. 158-169
Author(s):  
Rasmita Lenka ◽  
Koustav Dutta ◽  
Ashimananda Khandual ◽  
Soumya Ranjan Nayak
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Processing ◽  
Deep Learning ◽  
Early Detection ◽  
Digital Image Processing ◽  
Medical Science ◽  
Medical Image Processing ◽  
The World ◽  
Medical Reports

The chapter focuses on application of digital image processing and deep learning for analyzing the occurrence of malaria from the medical reports. This approach is helpful in quick identification of the disease from the preliminary tests which are carried out in a person affected by malaria. The combination of deep learning has made the process much advanced as the convolutional neural network is able to gain deeper insights from the medical images of the person. Since traditional methods are not able to detect malaria properly and quickly, by means of convolutional neural networks, the early detection of malaria has been possible, and thus, this process will open a new door in the world of medical science.

scholarly journals A comparative study of rice variety classification based on deep learning and hand-crafted features

2020 ◽  
Vol 14 (1) ◽  
pp. 1-10
Author(s):  
Vinh TRUONG HOANG ◽  
Duc Phan Van Hoai ◽  
Thongchai Surinwarangkoon ◽  
Huu-Thanh Duong ◽  
Kittikhun Meethongjan
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Comparative Study ◽  
Efficient Method ◽  
Rice Variety ◽  
Automation System ◽  
Rice Seed ◽  
Quality Inspection ◽  
The World ◽  
Variety Classification

Rice is vital to people all around the world. The demand for an efficient method in rice seed variety classification is one of the most essential tasks for quality inspection. Currently, this task is done by technicians based on experience by investigating the similarity of colour, shape and texture of rice. Therefore, we propose to find an appropriate process to develop an automation system for rice recognition. In this paper, several hand-crafted descriptors and Convolutional Neural Networks (CNN) methods are evaluated and compared. The experiment is simulated on the VNRICE dataset on which our method shows a significant result. The highest accuracy obtained is 99.04% by using DenNet21 framework.

scholarly journals Classification Using Neural Networks and Deep Learning

2020 ◽  
Author(s):  
Raju Singh
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Training Images ◽  
The World ◽  
Insight Into

This report is an insight into the world of deep learning and CNN networks. It is an attempt to perform classification using neural network and deep learning for a given dataset (which is a subset from the MNIST dataset). The MNIST dataset contains 70,000 images of handwritten digits, divided into 60,000 training images and 10,000 testing images.

scholarly journals Exploration of Pipelines from the use of GPR Data by Neural Network

2019 ◽  
Vol 8 (2S11) ◽  
pp. 3711-3715
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Ground Penetrating Radar ◽  
Buried Pipes ◽  
Adaptive Neural Networks ◽  
The World ◽  
Systematic Training ◽  
Ground Penetrating

Noticing about the buried pipes is a important issue, In many regions of the world. In spite of the fact that several techniques are there. This literature is used to find out the underground pipes automatically that provides accuracy execution is underway. Which gave amazing results Achieved by the deep learning of the different discoveries found in this article offer a pipeline to detect anti-personnel pipes Adaptive Neural Networks ( applied to the Ground Penetrating Radar (GPR). The proposed algorithm is suitable to recognize if the scanning format has been received. The acquisition of GPR has a track of anti-personnel pipes. The validity of the said system is made on a real GPR receipt, although systematic training can be done to have relied upon data generated by achievements. Based on the results 95% of the accuracy of detection got achieved without testing acquisition of pipes.

scholarly journals Traffic Sign Classification Using Convolutional Neural Networks and Computer Vision

2021 ◽  
Vol 12 (3) ◽  
pp. 4244-4250
Author(s):  
Anuraag Velamati Et.al
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Image Classification ◽  
Human Beings ◽  
Traffic Sign ◽  
The World ◽  
Traffic Sign Classification

The world is quickly and continuously advancing towards better technological advancements that will make life quite easier for us, human beings [22]. Humans are looking for more interactive and advanced ways to improve their learning. One such dream is making a machine think like a computer, which lead to innovations like AI and deep learning [25]. The world is running at a higher pace in the domain of AI, deep learning, robotics and machine learning Using this knowledge and technology, we could develop anything right now [36]. As a part of sub-domain, the introduction of Convolution Neural Networks made deep learning extensively strong in the domain of image classification and detection [1]..The research that we have conducted is one of its kind. Our research used Convolution Neural Network, TensorFlow and Keras.

scholarly journals Predictability in natural images determines V1 firing rates and synchronization: A deep neural network approach

2020 ◽  
Author(s):  
Cem Uran ◽  
Alina Peter ◽  
Andreea Lazar ◽  
William Barnes ◽  
Johanna Klon-Lipok ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Recognition ◽  
Visual Processing ◽  
Deep Neural Network ◽  
Natural Images ◽  
Natural Image ◽  
Natural Image Statistics ◽  
Neural Network Approach ◽  
Firing Rates

AbstractFeedforward deep neural networks for object recognition are a promising model of visual processing and can accurately predict firing-rate responses along the ventral stream. Yet, these networks have limitations as models of various aspects of cortical processing related to recurrent connectivity, including neuronal synchronization and the integration of sensory inputs with spatio-temporal context. We trained self-supervised, generative neural networks to predict small regions of natural images based on the spatial context (i.e. inpainting). Using these network predictions, we determined the spatial predictability of visual inputs into (macaque) V1 receptive fields (RFs), and distinguished low- from high-level predictability. Spatial predictability strongly modulated V1 activity, with distinct effects on firing rates and synchronization in gamma-(30-80Hz) and beta-bands (18-30Hz). Furthermore, firing rates, but not synchronization, were accurately predicted by a deep neural network for object recognition. Neural networks trained to specifically predict V1 gamma-band synchronization developed large, grating-like RFs in the deepest layer. These findings suggest complementary roles for firing rates and synchronization in self-supervised learning of natural-image statistics.

The Exploration of Autonomous Vehicles

2020 ◽  
pp. 108-122
Author(s):  
Anthony J. Gephardt ◽  
Elizabeth Baoying Wang
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Intelligent Agents ◽  
Autonomous Vehicles ◽  
Learning Processes ◽  
Artificial Intelligent ◽  
The World ◽  
History Of ◽  
The Creation

This chapter explores the world of autonomous vehicles. Starting from the beginning, it covers the history of the automobile dating back to 1769. It explains how the first production automobile came about in 1885. The chapter dives into the history of auto safety, ranging from seatbelts to full-on autonomous features. One of the main focuses is the creation and implementation of artificial intelligent (AI), neural networks, intelligent agents, and deep Learning Processes. Combining the hardware on the vehicle with the intelligence of AI creates what we know as autonomous vehicles today.

Sign in / Sign up

Export Citation Format

Share Document