Invited Research Talk: Measuring Generalization in EEG Foundation Models
- Aditya Kommineni, University of Southern California; Dimitra Emmanouilidou, Microsoft
Over the past few years, there has been an increasing interest towards building EEG foundation models that provide generalized representations for EEG signals, which are able to provide noticeable performance improvements over supervised baseline methods. While there have been numerous models that have been proposed, limited work has been performed in evaluation and interpretability of these foundation models, which could further help guide future model building. This talk will discuss a multi-dimensional evaluation framework for EEG foundation models, based on parameter, sample and channel efficiency that reflect real-world constraints in EEG deployment. Through this evaluation, we show that in a multitude of aspects, EEG foundation models fail to show performance gains over supervised baselines. Additionally, through a simulation based framework, synthetic EEG signals with controllable oscillatory and aperiodic components are used as inputs to EEG foundation models, to identify whether EEG foundation models capture both aperiodic and oscillatory components. We find that most reconstruction based EEG foundation models tend to have an aperiodic low frequency bias which is reflected in the models capability to better capture subject specific constructs over task specific information. Altogether, our analysis highlights deficiencies in current EEG foundation models and sheds light on missing components that could help improve generalization.
-
-
Aditya Kommineni
PhD Student
University of Southern California
-
Dimitra Emmanouilidou
Senior Researcher
-
-
Series: Cryptography Talk Series
-
-
-
-
TruthTable: A Verifiable Query Engine
- Bharath Namboothiry,
- Kim Laine
-
-
-
-
-
-
Efficient Homomorphic Integer Computer from CKKS
- Jaehyung Kim
-
Fuzzy Extractors are Practical
- Melissa Chase,
- Amey Shukla
-
-
-
-
Lattice-Based Accumulator and Application to Anonymous Credential Revocation
- Victor Youdom Kemmoe,
- Betül Durak
-
Efficient Secure Aggregation for Federated Learning
- Varun Madathil,
- Melissa Chase
-
-
-
-
Hamming Quasi-Cyclic
- Edoardo Persichetti
-
-
-
Attestations over TLS 1.3 and ZKP
- Sofía Celi
-
A Closer Look at Falcon
- Jonas Janneck
-
Quantum Lattice Enumeration in Limited Depth, Fernando Virdia
- Fernando Virdia