activity
20162021
most citedMaking Good on LSTMs' Unfulfilled Promise

5 citations · 6 across the 5 of their papers we have counts for

collaborators

14 papers

cs.SD2021

Learned complex masks for multi-instrument source separation

Andreas Jansson, Rachel M. Bittner, Nicola Montecchio +1

Music source separation in the time-frequency domain is commonly achieved by applying a soft or binary mask to the magnitude component of (complex) spectrograms. The phase componen…

cs.CL2021

Relational Weight Priors in Neural Networks for Abstract Pattern Learning and Language Modelling

Radha Kopparti, Tillman Weyde

Deep neural networks have become the dominant approach in natural language processing (NLP). However, in recent years, it has become apparent that there are shortcomings in systema…

cs.LG2020

Anti-Transfer Learning for Task Invariance in Convolutional Neural Networks for Speech Processing

Eric Guizzo, Tillman Weyde, Giacomo Tarroni

We introduce the novel concept of anti-transfer learning for speech processing with convolutional neural networks. While transfer learning assumes that the learning process for a t…

eess.AS2020

Multi-Time-Scale Convolution for Emotion Recognition from Speech Audio Signals

Eric Guizzo, Tillman Weyde, Jack Barnett Leveson

Robustness against temporal variations is important for emotion recognition from speech audio, since emotion is ex-pressed through complex spectral patterns that can exhibit signif…

cs.LG2020

Weight Priors for Learning Identity Relations

Radha Kopparti, Tillman Weyde

Learning abstract and systematic relations has been an open issue in neural network learning for over 30 years. It has been shown recently that neural networks do not learn relatio…

cs.LG20195 cited

Making Good on LSTMs' Unfulfilled Promise

Daniel Philps, Artur d'Avila Garcez, Tillman Weyde

LSTMs promise much to financial time-series analysis, temporal and cross-sectional inference, but we find that they do not deliver in a real-world financial management task. We exa…