Jekaterina Novikova
Director of Machine Learning Research @ Winterlight Labs | Cambridge Cognition
robustness
generalizability
clustering
large language models
speech
language
dimensionality reduction
dementia
depression
data-driven symptoms
symptoms
ml for health
3
presentations
2
number of views
SHORT BIO
Jekaterina Novikova is a Director of Machine Learning Research at Cambridge Cognition (prev. Winterlight Labs), where she leads a research group in the area of Natural Language Processing and Machine Learning, with the focus on the intersection of Language Technology and Machine Learning in Healthcare. Jekaterina is also a Science Lead at the ARVA non-profit organization, where she leads research efforts towards creating an open-source knowledge base of failure modes for AI models and datasets. Her aim is to make Machine Learning approaches more trustworthy and more interpretable in real world scenarios in order for them to be successfully applied to interdisciplinary areas, such as Healthcare, Spoken Dialogue Systems and Human-Robot Interaction.
Presentations
Generalizability and Robustness of Large Language Models Detecting Alzheimer’s Disease from Speech
Jekaterina Novikova
Data-driven Approach to Differentiating between Depression and Dementia from Noisy Speech and Language Data
Malikeh Ehghaghi and 2 other authors
Robustness and Sensitivity of BERT Models Predicting Alzheimer's Disease from Text
Jekaterina Novikova