Foundational GPT Model for MEG

1 code implementation • 14 Apr 2024 • Richard Csaky, Mats W. J. van Es, Oiwi Parker Jones, Mark Woolrich

We compare the performance of these deep learning models with standard linear autoregressive (AR) modelling on MEG data.

EEG

Group-level Brain Decoding with Deep Learning

1 code implementation • 27 May 2022 • Richard Csaky, Mats Van Es, Oiwi Parker Jones, Mark Woolrich

Decoding brain imaging data are gaining popularity, with applications in brain-computer interfaces and the study of neural representations.

Brain Decoding Feature Importance

The Gutenberg Dialogue Dataset

1 code implementation • EACL 2021 • Richard Csaky, Gabor Recski

Large datasets are essential for neural modeling of many NLP tasks.

Proposal Towards a Personalized Knowledge-powered Self-play Based Ensemble Dialog System

no code implementations • 11 Sep 2019 • Richard Csaky

This is the application document for the 2019 Amazon Alexa competition.

Deep Learning Based Chatbot Models

1 code implementation • 23 Aug 2019 • Richard Csaky

Finally, I conduct a detailed analysis of how the vanilla model performs on conversational data by comparing it to previous chatbot models and how the additional features affect the quality of the generated responses.

Chatbot Language Modelling +1

Improving Neural Conversational Models with Entropy-Based Data Filtering

2 code implementations • ACL 2019 • Richard Csaky, Patrik Purgai, Gabor Recski

Current neural network-based conversational models lack diversity and generate boring responses to open-ended utterances.

Response Generation