AI Verification Application : Development of an Application for ArtificialNeural Network Verification and Investigation of Hyperparameters for Single Shot Detection Models

Detta är en Kandidat-uppsats från KTH/Hälsoinformatik och logistik; KTH/Hälsoinformatik och logistik

Författare: Joel Vik; Fredrik Lindgren; [2020]

Nyckelord: ;

Sammanfattning: Abstract Hyperparameter tuning for Artificial Neural Network models is an important part in the process of producing the best model for a given task. The process heavily relies on the availability of time and computing resources. For Artifi-cial Neural Network models intended to run on embedded systems, models are tuned and trained on powerful computers with far more computing re-sources, prior to deployment on the embedded system itself. Consequently, the performance of these models require validation on the target embedded system. This is required since the performance of the models might be insuf-ficient when executed on an embedded system with limited computing re-sources. The process of validating can be a time-consuming and tedious task. This thesis covers the development of an application prototype which eases the process of validating pre-compiled Artificial Neural Network models on a target embedded system. In addition, the thesis covers an analysis of hyperpa-rameter tuning algorithms, along with an investigation of which parameters are important to tune in Convolutional Neural Networks for Single Shot De-tection. An application prototype was developed, and its functionality was val-idated. An analysis of tuning algorithms was conducted, however, no indefi-nite conclusions could be drawn, since the results were conflicting, and the sample size was too small. Through the investigation of hyperparameters, op-timizer learning rate was determined to be important to tune in Convolutional Neural Networks for Single Shot Detection. Further work, with a larger sample size, might make it possible to identify additional important parameters. KeywordsArtificial Neural Network, Convolutional Neural Network, Hyperparameter tuning, Single Shot Detection, Embedded Machine Learning, Python, Grid search, Random search, Bayesian optimization, automated hyperparameter tuning

  HÄR KAN DU HÄMTA UPPSATSEN I FULLTEXT. (följ länken till nästa sida)