15 citations · 36 across the 9 of their papers we have counts for
9 papers
Is More Data Worth the Cost? Dataset Scaling Laws in a Tiny Attention-Only Decoder
Götz-Henrik Wiegand, Lorena Raichle, Rico Städeli +3
Training Transformer language models is expensive, as performance typically improves with increasing dataset size and computational budget. Although scaling laws describe this tren…
A Convexity-dependent Two-Phase Training Algorithm for Deep Neural Networks
Tomas Hrycej, Bernhard Bermeitinger, Massimo Pavone +2
The key task of machine learning is to minimize the loss function that measures the model fit to the training data. The numerical methods to do this efficiently depend on the prope…
Efficient Neural Network Training via Subset Pretraining
Jan Spörer, Bernhard Bermeitinger, Tomas Hrycej +2
In training neural networks, it is common practice to use partial gradients computed over batches, mostly very small subsets of the training set. This approach is motivated by the…
Reducing the Transformer Architecture to a Minimum
Bernhard Bermeitinger, Tomas Hrycej, Massimo Pavone +2
Transformers are a widespread and successful model architecture, particularly in Natural Language Processing (NLP) and Computer Vision (CV). The essential innovation of this archit…
Make Deep Networks Shallow Again
Bernhard Bermeitinger, Tomas Hrycej, Siegfried Handschuh
Deep neural networks have a good success record and are thus viewed as the best architecture choice for complex applications. Their main shortcoming has been, for a long time, the…
Number of Attention Heads vs Number of Transformer-Encoders in Computer Vision
Tomas Hrycej, Bernhard Bermeitinger, Siegfried Handschuh
Determining an appropriate number of attention heads on one hand and the number of transformer-encoders, on the other hand, is an important choice for Computer Vision (CV) tasks us…
Training Neural Networks in Single vs Double Precision
Tomas Hrycej, Bernhard Bermeitinger, Siegfried Handschuh
The commitment to single-precision floating-point arithmetic is widespread in the deep learning community. To evaluate whether this commitment is justified, the influence of comput…
Representational Capacity of Deep Neural Networks -- A Computing Study
Bernhard Bermeitinger, Tomas Hrycej, Siegfried Handschuh
There is some theoretical evidence that deep neural networks with multiple hidden layers have a potential for more efficient representation of multidimensional mappings than shallo…
Singular Value Decomposition and Neural Networks
Bernhard Bermeitinger, Tomas Hrycej, Siegfried Handschuh
Singular Value Decomposition (SVD) constitutes a bridge between the linear algebra concepts and multi-layer neural networks---it is their linear analogy. Besides of this insight, i…