phd candidate at berkeley working (with the amazing prof. bin yu) on interpretable machine learning across domains 🧠💊️🦠
if you want to chat about research ideas or how to use data-science for good, drop me an e-mail!
phd candidate at berkeley working (with the amazing prof. bin yu) on interpretable machine learning across domains 🧠💊️🦠
if you want to chat about research ideas or how to use data-science for good, drop me an e-mail!
| year | title | authors | tags | paper | code | misc |
|---|---|---|---|---|---|---|
| '22 | VeridicalFlow: a Python package for building trustworthy data science pipelines with PCS | duncan*, kapoor*, agarwal*, singh*, & yu | 🔎 ml | joss | ||
| '21 | Adaptive wavelet distillation from neural networks through interpretations | ha, singh, et al. | 🔎 ml | neurips | ||
| '21 | imodels: a python package for fitting interpretable models | singh*, nasseri*, et al. | 🔎 ml | joss | ||
| '21 | Matched sample selection with GANs for mitigating attribute confounding | singh, balakrishnan, & perona | ml | cvpr workshop | ||
| '21 | Revisiting complexity and the bias-variance tradeoff | dwivedi*, singh*, yu & wainwright | ml | topml workshop | ||
| '21 | developing reliable clinical decision rules: a case study in identifying blunt abdominal trauma in children | kornblith*, singh* et al. | 📊 🔎 💊 | SAEM abstract | ||
| '21 | Interpretable deep learning for accurate molecular partner prediction in clathrin-mediated endocytosis | singh*, li*, et al. | 📊 🦠 | in prep | ||
| '20 | Curating a COVID-19 data repository and forecasting county-level death counts in the United States | altieri et al. | 📊 🦠 | hdsr | ||
| '20 | interpretations are useful: penalizing explanations to align neural networks with prior knowledge | rieger, singh, murdoch & yu | 🔎 ml | icml | ||
| '20 | transformation importance with applications to cosmology | singh*, ha*, lanusse, boehm, liu & yu | 🔎 🌌 ml | iclr workshop (spotlight) | ||
| '19 | disentangled attribution curves for interpreting random forests and boosted trees | devlin, singh, murdoch & yu | 🔎 ml | arxiv | ||
| '19 | interpretable machine learning: definitions, methods, and applications | Murdoch*, Singh*, et al. | 🔎 ml | pnas | ||
| '19 | hierarchical interpretations for neural network predictions | Singh*, Murdoch*, & Yu | 🔎 ml | ICLR | ||
| '18 | large scale image segmentation with structured loss based deep learning for connectome reconstruction | Funke*, Tschopp*, et al. | ml 🧠 | TPAMI | ||
| '18 | linearization of excitatory synaptic integration at no extra cost | Morel, Singh, & Levy | 🧠 | J Comp Neuro | ||
| '17 | a consensus layer V pyramidal neuron can sustain interpulse-interval coding | Singh & Levy | 🧠 | Plos One | ||
| '17 | a constrained, weighted-l1 minimization approach for joint discovery of heterogeneous neural connectivity graphs | Singh, Wang, & Qi | ml 🧠 | neurips Workshop | , |
Some posts in ml research and organizing different papers.
Resources including teaching slides, research overview slides, and coding projects.
A rough set of notes which may serve as useful reference for people in machine learning / neuroscience.
phd research in interpretable ml
developed deep learning models for pathology
developed methods for causal benchmarking of fairness in computer vision models
developed methods for interpreting medical machine-learning models
Worked on unsupervised pretraining of CNNs for semantic segmentation
Contributed to development of novel weighted-L1, multi-task Gaussian graphical models
Contributed to enhanced ML implementations for neural image segmentation
Simulated stochastic neurons to determine mutual information, variability, energy efficiency, and threshold
Simulated extracellular neural recordings via Neurocube Matlab scripts
Developed web app for simultaneous task coordination + Android app to increase the data storage capacity of QR codes.
I've been lucky to be advised by / collaborate with many amazing people
It has been my pleasure to help advise some incredible undergrads at berkeley -- check them out!
