I'm a PhD student at Carnegie Mellon in a joint program between Machine Learning and Neural Computation. I study how language is processed both by the brain and by machines. To get closer to this goal, I work with my advisors - Tom Mitchell and Leila Wehbe - to investigate the representations in the brain as subjects read naturalistic text in neuroimaging devices (both fMRI and Magnetoencephalography), as well as the representations of the same text as it is passed through current natural language processing models. My research is supported by the NSF graduate fellowship. Before beginning my graduate studies at CMU, I received a B.S. in both Computer Science and Cognitive Science at Yale University.

I also enjoy taking care of (helpful) bacteria and turning them into yogurt and sourdough bread from time to time.


Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)
M. Toneva and L. Wehbe
NeurIPS, 2019
[abs] [pdf] [code]
Inducing brain-relevant bias in natural language processing models
D. Schwartz, M. Toneva , and L. Wehbe
NeurIPS, 2019
[abs] [pdf] [code]
Investigating Task Effects on Brain Activity During Stimulus Presentation in MEG
M. Toneva*, O.Stretcu*, B. Poczos, and T. Mitchell
Human Brain Mapping, 2019
An Empirical Study of Example Forgetting during Deep Neural Network Learning
M. Toneva*, A. Sordoni*, R. Tachet des Combes*, A. Trischler, Y. Bengio, and G. Gordon
ICLR, 2019
[abs] [pdf] [code] [open review]
Word Length Processing in Left Lateraloccipital through Region-to-Region Connectivity: an MEG Study
M. Toneva and T. Mitchell
Human Brain Mapping, 2018
MEG Representational Similarity Analysis Implicates Hierarchical Integration in Sentence Processing
M. Toneva*, N. Rafidi*, D. Schwartz*, S. Jat, and T. Mitchell
Human Brain Mapping, 2018
Applying artificial vision models to human scene understanding
E. M. Aminoff, M. Toneva, A. Shrivastava, X. Chen, I. Misra, A. Gupta, and M. J. Tarr
Frontiers in Computational Neuroscience, 2015
[abs] [pdf]
Scene-Space Encoding within the Functional Scene-Selective Network
E. M. Aminoff, M. Toneva, A. Gupta, and M. J. Tarr
Journal of Vision, 2015
Towards a model for mid-level feature representation of scenes
M. Toneva, E. M. Aminoff, A. Gupta, and M. Tarr
Oral presentation. WIML NIPS workshop, 2014
An Exploration of Social Grouping: Effects of Behavioral Mimicry, Appearance, and Eye Gaze
A. Nawroj, M. Toneva, H. Admoni, and B. Scassellati
Oral presentation. In proceedings of the 36th Annual Conference of the Cognitive Science Society (Cogsci 2014)
[abs] [pdf]
The Physical Presence of a Robot Tutor Increases Cognitive Learning Gains
D. Leyzberg, S. Spaulding, M. Toneva, and B. Scassellati
Poster. In Proceedings of the 34th Annual Conference of the Cognitive Science Society (Cogsci 2012)
[abs] [pdf]
Robot gaze does not reflexively cue human attention
H. Admoni, C. Bank, J. Tan, M. Toneva, and B. Scassellati
Poster. In Proceedings of the 33rd Annual Conference of the Cognitive Science Society (Cogsci 2011)
[abs] [pdf]


During Fall 2016, I served as a Teaching Assistant for the course Convex Optimization taught by Ryan Tibshirani and Javier Peña, and was recognized with the ML TA award.

During the summer of 2016, I was fortunate to teach a lecture series on machine learning for neuroscientific applications as a part of the 2016 Multimodal Neuroimaging Training Program. MNTP is a summer program aimed at graduate students trained in neuroscience who would like to gain more experience in a different neuroscientific modality.

My goal in putting together the curriculum for this machine learning module was to give an intuitive overview of machine learning concepts that are useful for working with neuroscience data.

Lecture 1: classification (naive Bayes, SVM, kNN) & regression (linear) [audio did not work, so no video for this one] [slides]

Lecture 2: model selection (overfitting, cross validation, feature selection, regularization) & significance testing (permutation test, multiple comparison corrections) [slides]

Lecture 3: dimensionality reduction (PCA, ICA, CCA, Laplacian eigenmaps) & clustering (k-means, spectral clustering, divisive clustering, agglomerative clustering) [slides]

Lecture 4: latent variable models (HMM), reinforcement learning, deep learning (RNN, LSTM, DBN, CNN), AlphaGo algorithm details [slides]