In recent years, the state-of-the-art in computer vision has improved immensely due to increased use of convolutional neural networks (CNN). However, the best-performing models are typically complex and too slow or too large for mobile use. We investigate whether the power of these large models can be transferred to smaller models and used in mobile applications. A small CNN model was designed based on VGG Net. Using transfer learning, three pre-trained ImageNet networks were tuned to perform hand-drawn image classification. The models were evaluated on their predictive power and the best model was compressed to the small CNN model using knowledge distillation, a flavor of model compression. We found a small but significant improvement in c...
Despite the rapid progress in the field of machine learning and artificial neural networks, many hur...
Despite the rapid progress in the field of machine learning and artificial neural networks, many hur...
This master thesis tackles the problem of unsupervised learning of useful and interpretable represen...
In recent years, the state-of-the-art in computer vision has improved immensely due to increased use...
In recent years, the state-of-the-art in computer vision has improved immensely due to increased use...
In recent years, the state-of-the-art in computer vision has improved immensely due to increased use...
In recent years, the state-of-the-art in computer vision has improved immensely due to increased use...
With the recent advances in deep learning, the gaze estimation models reached new levels, in terms o...
With the recent advances in deep learning, the gaze estimation models reached new levels, in terms o...
With the recent advances in deep learning, the gaze estimation models reached new levels, in terms o...
In this research project we have compressed the model size of a generative neural network trained to...
In this research project we have compressed the model size of a generative neural network trained to...
In this research project we have compressed the model size of a generative neural network trained to...
Having a well representative and adequate amount of data samples plays an important role in the succ...
Having a well representative and adequate amount of data samples plays an important role in the succ...
Despite the rapid progress in the field of machine learning and artificial neural networks, many hur...
Despite the rapid progress in the field of machine learning and artificial neural networks, many hur...
This master thesis tackles the problem of unsupervised learning of useful and interpretable represen...
In recent years, the state-of-the-art in computer vision has improved immensely due to increased use...
In recent years, the state-of-the-art in computer vision has improved immensely due to increased use...
In recent years, the state-of-the-art in computer vision has improved immensely due to increased use...
In recent years, the state-of-the-art in computer vision has improved immensely due to increased use...
With the recent advances in deep learning, the gaze estimation models reached new levels, in terms o...
With the recent advances in deep learning, the gaze estimation models reached new levels, in terms o...
With the recent advances in deep learning, the gaze estimation models reached new levels, in terms o...
In this research project we have compressed the model size of a generative neural network trained to...
In this research project we have compressed the model size of a generative neural network trained to...
In this research project we have compressed the model size of a generative neural network trained to...
Having a well representative and adequate amount of data samples plays an important role in the succ...
Having a well representative and adequate amount of data samples plays an important role in the succ...
Despite the rapid progress in the field of machine learning and artificial neural networks, many hur...
Despite the rapid progress in the field of machine learning and artificial neural networks, many hur...
This master thesis tackles the problem of unsupervised learning of useful and interpretable represen...