1 code implementation • 27 Mar 2024 • Philip Kenneweg, Alexander Schulz, Sarah Schröder, Barbara Hammer
We combine the learning rate distributions thus found and show that they generalize to better performance with respect to the problem of catastrophic forgetting.
1 code implementation • 27 Mar 2024 • Philip Kenneweg, Sarah Schröder, Alexander Schulz, Barbara Hammer
It is problematic that most debiasing approaches are directly transferred from word embeddings, therefore these approaches fail to take into account the nonlinear nature of sentence embedders and the embeddings they produce.
1 code implementation • 26 Mar 2024 • Isaac Roberts, Alexander Schulz, Luca Hermes, Barbara Hammer
Attention based Large Language Models (LLMs) are the state-of-the-art in natural language processing (NLP).
no code implementations • 27 Jan 2024 • Sarah Schröder, Alexander Schulz, Fabian Hinder, Barbara Hammer
Furthermore, we formally analyze cosine based scores from the literature with regard to these requirements.
1 code implementation • 15 Jun 2022 • André Artelt, Alexander Schulz, Barbara Hammer
Dimensionality reduction is a popular preprocessing and a widely used tool in data mining.
no code implementations • 28 Mar 2022 • Sarah Schröder, Alexander Schulz, Philip Kenneweg, Robert Feldhans, Fabian Hinder, Barbara Hammer
Furthermore, we thoroughly investigate the existing cosine-based scores and their limitations in order to show why these scores fail to report biases in some situations.
1 code implementation • 21 Feb 2022 • Lisa Kühnel, Alexander Schulz, Barbara Hammer, Juliane Fluck
Recent developments in transfer learning have boosted the advancements in natural language processing tasks.
no code implementations • 15 Nov 2021 • Sarah Schröder, Alexander Schulz, Philip Kenneweg, Robert Feldhans, Fabian Hinder, Barbara Hammer
However, lately some works have raised doubts about these metrics showing that even though such metrics report low biases, other tests still show biases.
1 code implementation • 4 May 2021 • Benjamin Paaßen, Alexander Schulz, Barbara Hammer
In this paper, we introduce the reservoir stack machine, a model which can provably recognize all deterministic context-free languages and circumvents the training problem by training only the output layer of a recurrent net and employing auxiliary information during training about the desired interaction with a stack.
1 code implementation • 14 Sep 2020 • Benjamin Paaßen, Alexander Schulz, Terrence C. Stewart, Barbara Hammer
Differentiable neural computers extend artificial neural networks with an explicit memory without interference, thus enabling the model to perform classic computation tasks such as graph traversal.
no code implementations • 12 Feb 2020 • Benjamin Paassen, Alexander Schulz
In recent years, Neural Turing Machines have gathered attention by joining the flexibility of neural networks with the computational capabilities of Turing machines.
1 code implementation • 19 Sep 2019 • Alexander Schulz, Fabian Hinder, Barbara Hammer
So far, most methods in the literature investigate the decision of the model for a single given input datum.
no code implementations • 25 Nov 2017 • Benjamin Paaßen, Alexander Schulz, Janne Hahne, Barbara Hammer
Machine learning models in practical settings are typically confronted with changes to the distribution of the incoming data.