Essays about: "CNN architecture"
Showing result 1 - 5 of 115 essays containing the words CNN architecture.
-
1. CNN-LSTM architecture for predicting hazardous driving situations
University essay from Göteborgs universitet/Institutionen för data- och informationsteknikAbstract : This study aims to investigate how a CNN-LSTM model can be used together with recorded vehicle data from trucks and external weather data in order to predict a hazardous driving situation. The dataset consists of three-second-long driving snippets from customer and development trucks registered within Europe. READ MORE
-
2. ANOMALY DETECTION FOR INDUSTRIAL APPLICATIONS USING COMMODITY HARDWARE
University essay from Mälardalens universitet/Akademin för innovation, design och teknikAbstract : As the Automotive industry is heavily regulated from a quality point of view, excellence in pro-duction is obligatory. Due to the fact that removing human error from humans is impossible, new solutions must be found. READ MORE
-
3. Object Recognition in Satellite imagesusing improved ConvolutionalRecurrent Neural Network
University essay from Blekinge Tekniska Högskola/Institutionen för datavetenskapAbstract : Background:The background of this research lies in detecting the images from satellites. The recognition of images from satellites has become increasingly importantdue to the vast amount of data that can be obtained from satellites. This thesisaims to develop a method for the recognition of images from satellites using machinelearning techniques. READ MORE
-
4. The impact of pruning Convolutional Neural Networks when classifying skin cancer
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Over the past few years, there have been multiple reports showcasing how Convolutional Neural Networks (CNNs) can be used to classify if skin lesions are cancerous or non-cancerous. However, a limitation of CNNs is the large number of parameters resulting in high computation times. READ MORE
-
5. Evaluation of deep learning methods for industrial automation
University essay from Umeå universitet/Institutionen för datavetenskapAbstract : The rise and adaptation of the transformer architecture from natural language processing to visual tasks have proven a useful and powerful tool. Subsequent architectures such as visual transformers (ViT) and shifting window (SWIN) transformers have proven to be comparable and oftentimes exceed convolutional neural networks (CNNs) in terms of accuracy. READ MORE