In representation learning we are interested in how data is represented by different models. Representations from different models are often compared by training a new model on a downstream task using the representations and testing their performance. However, this method is not always applicable and it gives limited insight into the representations. In this thesis, we compare natural image representations from classification models and the generative model BigGAN using two other approaches. The first approach compares the geometric clustering of the representations and the second approach compares if the pairwise similarity between images is similar between different models. All models are large pre-trained models trained on ImageNet and t...
Recent neural network advances have lead to models that can be used for a variety of image classific...
This electronic version was submitted by the student author. The certified thesis is available in th...
Generative models are a family of machine learning algorithms that are aspire to enable computers to...
Efficient representations of observed input data have been shown to significantly accelerate the per...
Despite the rapid progress in the field of machine learning and artificial neural networks, many hur...
Although generative adversarial networks (GANs) have achieved state-of-the-art results in generating...
The success of machine learning algorithms generally depends on data representation, and we hypothes...
Artificial neural networks at the present time gain notable popularity and show astounding results i...
Deep neural networks takes their strength in the representations, or features, that they internally ...
This master thesis tackles the problem of unsupervised learning of useful and interpretable represen...
Machine learning models for visual recognition tasks such as image recognition is a common research ...
Deep learning methods underlie much of the recent rapid progress in computer vision. These approache...
Deep learning has been widely used in real-life applications during the last few decades, such as fa...
Comparing representations of complex stimuli in neural network layers to human brain representations...
Evidence is mounting that ConvNets are the best representation learning method for recognition. In t...
Recent neural network advances have lead to models that can be used for a variety of image classific...
This electronic version was submitted by the student author. The certified thesis is available in th...
Generative models are a family of machine learning algorithms that are aspire to enable computers to...
Efficient representations of observed input data have been shown to significantly accelerate the per...
Despite the rapid progress in the field of machine learning and artificial neural networks, many hur...
Although generative adversarial networks (GANs) have achieved state-of-the-art results in generating...
The success of machine learning algorithms generally depends on data representation, and we hypothes...
Artificial neural networks at the present time gain notable popularity and show astounding results i...
Deep neural networks takes their strength in the representations, or features, that they internally ...
This master thesis tackles the problem of unsupervised learning of useful and interpretable represen...
Machine learning models for visual recognition tasks such as image recognition is a common research ...
Deep learning methods underlie much of the recent rapid progress in computer vision. These approache...
Deep learning has been widely used in real-life applications during the last few decades, such as fa...
Comparing representations of complex stimuli in neural network layers to human brain representations...
Evidence is mounting that ConvNets are the best representation learning method for recognition. In t...
Recent neural network advances have lead to models that can be used for a variety of image classific...
This electronic version was submitted by the student author. The certified thesis is available in th...
Generative models are a family of machine learning algorithms that are aspire to enable computers to...