Sökning: "max-pooling"
Hittade 5 uppsatser innehållade ordet max-pooling.
1. Evaluating Robustness of a CNN Architecture introduced to the Adversarial Attacks
Kandidat-uppsats, Blekinge Tekniska HögskolaSammanfattning : Abstract: Background: From Previous research, state-of-the-art deep neural networks have accomplished impressive results on many images classification tasks. However, adversarial attacks can easily fool these deep neural networks by adding little noise to the input images. LÄS MER
2. A Deep Learning Application for Traffic Sign Recognition
Kandidat-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskapSammanfattning : Background: Traffic Sign Recognition (TSR) is particularly useful for novice driversand self-driving cars. Driver Assistance Systems(DAS) involves automatic trafficsign recognition. Efficient classification of the traffic signs is required in DAS andunmanned vehicles for safe navigation. LÄS MER
3. Evaluation of Machine Learning Primitives on a Digital Signal Processor
Master-uppsats, Linköpings universitet/Medie- och Informationsteknik; Linköpings universitet/Tekniska högskolanSammanfattning : Modern handheld devices rely on specialized hardware for evaluating machine learning algorithms. This thesis investigates the feasibility of using the digital signal processor, a part of the modem of the device, as an alternative to this specialized hardware. LÄS MER
4. Spatio-temporal prediction of residential burglaries using convolutional LSTM neural networks
Master-uppsats, KTH/GeoinformatikSammanfattning : The low amount solved residential burglary crimes calls for new and innovative methods in the prevention and investigation of the cases. There were 22 600 reported residential burglaries in Sweden 2017 but only four to five percent of these will ever be solved. LÄS MER
5. On-line Handwritten Signature Verification using Machine Learning Techniques with a Deep Learning Approach
Master-uppsats, Lunds universitet/Matematik LTHSammanfattning : The problem to be solved in this project is to distinguish two signatures from each other, with help of machine learning techniques. The main technique used is the comparison between two signatures and classifying if they are written by the same person (match) or not (no-match). LÄS MER