Honors & Awards
Walter V. and Idun Berry Postdoctoral Fellow, Stanford University (08/2015)
Bachelor of Arts, Brown University (2008)
Bachelor of Science, Brown University (2008)
Doctor of Philosophy, Stanford University, MATH-PHD (2013)
Bachelor of Science, Brown University, BS Math, BA Econ(5 yr program) (2008)
Nicholas Haber, Catalin Voss. "United States Patent Application 14/275851 Systems and methods for detection of behavior correlated with outside distractions in examinations"
Nicholas Haber, Catalin Voss. "United States Patent Application 61/821,921 System and Method for Analysis of Visual Viewer Reactions to Video Content. US Application"
Current Research and Scholarly Interests
I use AI models of of exploratory and social learning in order to better understand early human learning and development, and conversely, I use our understanding of early human learning to make robust AI models that learn in exploratory and social ways. Based on this, I develop AI-powered learning tools for children, geared in particular towards the education of those with developmental issues such as the Autism Spectrum Disorder and Attention Deficit Hyperactivity Disorder, in the mold of my work on the Autism Glass Project. My formal graduate training in pure mathematics involved extending partial differential equation theory in cases involving the propagation of waves through complex media such as the space around a black hole. Since then, I have transitioned to the use of machine learning in developing both learning tools for children with developmental disorders and AI and cognitive models of learning.
Feasibility Testing of a Wearable Behavioral Aid for Social Learning in Children with Autism
APPLIED CLINICAL INFORMATICS
2018; 9 (1): 129–40
Recent advances in computer vision and wearable technology have created an opportunity to introduce mobile therapy systems for autism spectrum disorders (ASD) that can respond to the increasing demand for therapeutic interventions; however, feasibility questions must be answered first.We studied the feasibility of a prototype therapeutic tool for children with ASD using Google Glass, examining whether children with ASD would wear such a device, if providing the emotion classification will improve emotion recognition, and how emotion recognition differs between ASD participants and neurotypical controls (NC).We ran a controlled laboratory experiment with 43 children: 23 with ASD and 20 NC. Children identified static facial images on a computer screen with one of 7 emotions in 3 successive batches: the first with no information about emotion provided to the child, the second with the correct classification from the Glass labeling the emotion, and the third again without emotion information. We then trained a logistic regression classifier on the emotion confusion matrices generated by the two information-free batches to predict ASD versus NC.All 43 children were comfortable wearing the Glass. ASD and NC participants who completed the computer task with Glass providing audible emotion labeling (n = 33) showed increased accuracies in emotion labeling, and the logistic regression classifier achieved an accuracy of 72.7%. Further analysis suggests that the ability to recognize surprise, fear, and neutrality may distinguish ASD cases from NC.This feasibility study supports the utility of a wearable device for social affective learning in ASD children and demonstrates subtle differences in how ASD and NC children perform on an emotion recognition task.
View details for DOI 10.1055/s-0038-1626727
View details for Web of Science ID 000428690000006
View details for PubMedID 29466819
View details for PubMedCentralID PMC5821509
Sparsifying machine learning models identify stable subsets of predictive features for behavioral detection of autism
2017; 8: 65
Autism spectrum disorder (ASD) diagnosis can be delayed due in part to the time required for administration of standard exams, such as the Autism Diagnostic Observation Schedule (ADOS). Shorter and potentially mobilized approaches would help to alleviate bottlenecks in the healthcare system. Previous work using machine learning suggested that a subset of the behaviors measured by ADOS can achieve clinically acceptable levels of accuracy. Here we expand on this initial work to build sparse models that have higher potential to generalize to the clinical population.We assembled a collection of score sheets for two ADOS modules, one for children with phrased speech (Module 2; 1319 ASD cases, 70 controls) and the other for children with verbal fluency (Module 3; 2870 ASD cases, 273 controls). We used sparsity/parsimony enforcing regularization techniques in a nested cross validation grid search to select features for 17 unique supervised learning models, encoding missing values as additional indicator features. We augmented our feature sets with gender and age to train minimal and interpretable classifiers capable of robust detection of ASD from non-ASD.By applying 17 unique supervised learning methods across 5 classification families tuned for sparse use of features and to be within 1 standard error of the optimal model, we find reduced sets of 10 and 5 features used in a majority of models. We tested the performance of the most interpretable of these sparse models, including Logistic Regression with L2 regularization or Linear SVM with L1 regularization. We obtained an area under the ROC curve of 0.95 for ADOS Module 3 and 0.93 for ADOS Module 2 with less than or equal to 10 features.The resulting models provide improved stability over previous machine learning efforts to minimize the time complexity of autism detection due to regularization and a small parameter space. These robustness techniques yield classifiers that are sparse, interpretable and that have potential to generalize to alternative modes of autism screening, diagnosis and monitoring, possibly including analysis of short home videos.
View details for DOI 10.1186/s13229-017-0180-6
View details for Web of Science ID 000418669700001
View details for PubMedID 29270283
View details for PubMedCentralID PMC5735531
Crowdsourced validation of a machine-learning classification system for autism and ADHD.
2017; 7 (5)
Autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD) together affect >10% of the children in the United States, but considerable behavioral overlaps between the two disorders can often complicate differential diagnosis. Currently, there is no screening test designed to differentiate between the two disorders, and with waiting times from initial suspicion to diagnosis upwards of a year, methods to quickly and accurately assess risk for these and other developmental disorders are desperately needed. In a previous study, we found that four machine-learning algorithms were able to accurately (area under the curve (AUC)>0.96) distinguish ASD from ADHD using only a small subset of items from the Social Responsiveness Scale (SRS). Here, we expand upon our prior work by including a novel crowdsourced data set of responses to our predefined top 15 SRS-derived questions from parents of children with ASD (n=248) or ADHD (n=174) to improve our model's capability to generalize to new, 'real-world' data. By mixing these novel survey data with our initial archival sample (n=3417) and performing repeated cross-validation with subsampling, we created a classification algorithm that performs with AUC=0.89±0.01 using only 15 questions.
View details for DOI 10.1038/tp.2017.86
View details for PubMedID 28509905
- The Feynman Propagator on Perturbations of Minkowski Space COMMUNICATIONS IN MATHEMATICAL PHYSICS 2016; 342 (1): 333-384
Use of machine learning for behavioral distinction of autism and ADHD.
Although autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD) continue to rise in prevalence, together affecting >10% of today's pediatric population, the methods of diagnosis remain subjective, cumbersome and time intensive. With gaps upward of a year between initial suspicion and diagnosis, valuable time where treatments and behavioral interventions could be applied is lost as these disorders remain undetected. Methods to quickly and accurately assess risk for these, and other, developmental disorders are necessary to streamline the process of diagnosis and provide families access to much-needed therapies sooner. Using forward feature selection, as well as undersampling and 10-fold cross-validation, we trained and tested six machine learning models on complete 65-item Social Responsiveness Scale score sheets from 2925 individuals with either ASD (n=2775) or ADHD (n=150). We found that five of the 65 behaviors measured by this screening tool were sufficient to distinguish ASD from ADHD with high accuracy (area under the curve=0.965). These results support the hypotheses that (1) machine learning can be used to discern between autism and ADHD with high accuracy and (2) this distinction can be made using a small number of commonly measured behaviors. Our findings show promise for use as an electronically administered, caregiver-directed resource for preliminary risk evaluation and/or pre-clinical screening and triage that could help to speed the diagnosis of these disorders.
View details for DOI 10.1038/tp.2015.221
View details for PubMedID 26859815
View details for PubMedCentralID PMC4872425
- Propagation of singularities around a Lagrangian submanifold of radial points Bulletin de la SMF 2015
PROPAGATION OF SINGULARITIES AROUND A LAGRANGIAN SUBMANIFOLD OF RADIAL POINTS
BULLETIN DE LA SOCIETE MATHEMATIQUE DE FRANCE
2015; 143 (4): 679-726
View details for Web of Science ID 000371649000003
- A Normal Form Around a Lagrangian Submanifold of Radial Points INTERNATIONAL MATHEMATICS RESEARCH NOTICES 2014: 4804-4821
- The Feynman propagator on perturbations of minkowski space. arXiv.org 2014
- Microlocal analysis of Lagrangian submanifolds of radial points Stanford University Thesis 2013
- Color-Permuting Automorphisms of Cayley Graphs Congressus Numerantium 2008; 190: 161-177