The far-reaching successes of deep neural networks in a wide variety of learning tasks have prompted research on how model properties account for high network performance. For a specific class of models whose activation functions are piecewise linear, one such property of interest is the number of linear regions that the network generates. Such models themselves define piecewise linear functions by partitioning input space into disjoint regions and fitting a different linear function on each such piece. It would be expected that the number or configuration of such regions would describe the model’s ability to fit complicated functions. However, previous works have shown difficulty in identifying linear regions as satisfactory predictors of ...
It is known that gradient flow in linear neural networks using Euclidean loss almost always avoids c...
In our work we aim to explore a general framework that addresses the fundamental problem of universa...
Recently geometric deep learning introduced a new way for machine learning algorithms to tackle poin...
Artificial neural networks at the present time gain notable popularity and show astounding results i...
In recent years, deep learning models have been widely used and are behind major breakthroughs acros...
Neural networks utilizing piecewise linear transformations between layers have in many regards becom...
Deep neural networks takes their strength in the representations, or features, that they internally ...
Policies produced by deep reinforcement learning are typically characterised by their learning curve...
In this dissertation, we explore the impact of geometry and topology on the capabilities of deep lea...
Despite the empirical success and widespread adoption of deep neural networks, methods for systemati...
Littmann E, Ritter H. Curvature estimation with a DCA neural network. In: Deutsche Arbeitsgemeinscha...
We show that deep ReLU neural network classifiers can see a low-dimensional Riemannian manifold stru...
In Machine Learning field, data characteristics usually vary over the space: the overall distributi...
The highly non-linear nature of deep neural networks causes them to be susceptible to adversarial ex...
Considering the broadness of the area of artificial intelligence, interpretations of the underlying ...
It is known that gradient flow in linear neural networks using Euclidean loss almost always avoids c...
In our work we aim to explore a general framework that addresses the fundamental problem of universa...
Recently geometric deep learning introduced a new way for machine learning algorithms to tackle poin...
Artificial neural networks at the present time gain notable popularity and show astounding results i...
In recent years, deep learning models have been widely used and are behind major breakthroughs acros...
Neural networks utilizing piecewise linear transformations between layers have in many regards becom...
Deep neural networks takes their strength in the representations, or features, that they internally ...
Policies produced by deep reinforcement learning are typically characterised by their learning curve...
In this dissertation, we explore the impact of geometry and topology on the capabilities of deep lea...
Despite the empirical success and widespread adoption of deep neural networks, methods for systemati...
Littmann E, Ritter H. Curvature estimation with a DCA neural network. In: Deutsche Arbeitsgemeinscha...
We show that deep ReLU neural network classifiers can see a low-dimensional Riemannian manifold stru...
In Machine Learning field, data characteristics usually vary over the space: the overall distributi...
The highly non-linear nature of deep neural networks causes them to be susceptible to adversarial ex...
Considering the broadness of the area of artificial intelligence, interpretations of the underlying ...
It is known that gradient flow in linear neural networks using Euclidean loss almost always avoids c...
In our work we aim to explore a general framework that addresses the fundamental problem of universa...
Recently geometric deep learning introduced a new way for machine learning algorithms to tackle poin...