About Me
I am the Vice President of Machine Learning at Chaos Industries, building the AI team, working on product strategies, and developing multi-modal large models. Before this, I was Principal ML Research Scientist, leading the ML team at Micron Technology Inc. as part of its Advanced Computing and Solution (ACS) group. I have firm belief that vision models have more capacity to capture information than language models, and self-supervised technique is the way to move forward if we want to even get close to "general intelligence". My ongoing research involves development of multi-task and multi-modal networks using large transformers. Applied research intrigues me, and my focus has always been on solving current probkems by building futuristic solutions.
I completed my PhD from Purdue University in 2019 under Prof. Eugenio Culurciello as part of e-Lab. During my PhD I was also the founding member of a successful start up FwdNxt where I led its machine learning team. I received my undergraduate degree from Indian Institute of Technology (IIT) Guwahati, India and my Masters degree from Hanyang University, South Korea in 2012 and 2014 respectively.
I am mostly interested in developing deep neural network architectures which not only stand out in terms of accuracy, but can also be used in real life applications. Scene understanding is an important part of any machine learning task and I am working on multi-task and multi-modal networks for self-driving vehicles, augmented reality, etc. This serves as a major motivation for me to develop networks which can not only run on GPUs but also on embedded devices such as NVIDIA Tegra and Micron Deep Learning Accelerator (MDLA). I have also been spending significant amount of time working on developing unsupervised techniques for image enhancement and segmentation of medical images.
My google scholar profile can be found here. To look into some of the codes written by me, go to my Github page.
Teaching Experience
Publications
- K. Giannios, Abhishek Chaurasia, C. Bueno, J.L. Riesterer, L. Pagano, T.P. Lo, G. Thibault, J.W. Gray, X. Song, B. DeLaRosa. "Towards Generalizability and Robustness in Biological Object Detection in Electron Microscopy Images" bioRxiv, 2023.11. 27.568889 [2023]
- S. Wadekar and Abhishek Chaurasia. "MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features." arXiv preprint arXiv:2209.15159 [2022]
- A.XM. Chang, P. Khopkar, B. Romanous, Abhishek Chaurasia, P. Estep, S. Windh, D. Vanesko, S.D.B. Mohideen, E. Culurciello. "Reinforcement Learning Approach for Mapping Applications to Dataflow-Based Coarse-Grained Reconfigurable Array." arXiv preprint arXiv:2205.13675 [2022]
- Abhishek Chaurasia, K. Giannios, G. Thibault, J.L. Riesterer, E.S. Stempinski, T.P. Lo, B. DeLaRosa, J.W. Gray. "Noise Reconstruction & Removal Network: A New Architecture to Denoise FIB-SEM Images." Microscopy and Microanalysis 28 (S1), 1506-1508 [2021]
- P. Zhang, S. Liu, Abhishek Chaurasia, D.J. Mlodzianoski, E. Culurciello, and F. Huang. "Analyzing complex single-molecule emission patterns with deep learning." Nature Methods, 15, pages 913–916 [2018]
- Abhishek Chaurasia, and E. Culurciello, "LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation." arXiv preprint arXiv:1707.03718 [2017]
- A. Paszke, Abhishek Chaurasia, S. Kim, and E. Culurciello, "ENet: A deep neural network architecture for real-time semantic segmentation." arXiv preprint arXiv:1606.02147 [2016]
- A.K. Mishra, Abhishek Chaurasia and D. Deb, "Prefrontal Cortex Motivated Cognitive Architecture for Multiple Robots." arXiv preprint arXiv:1411.3111 [2014]
- Abhishek Chaurasia, A. Jeph, and F.C-H. Rhee, "Interval type-2 fuzzy C-means using multiple kernels." In Fuzzy Systems (FUZZ), 2013 IEEE International Conference on, pp. 1-8. IEEE [2013]
- Abhishek Chaurasia, and A. Tripathi, "Six-rotor UAV helicopter dynamics and control: theory and simulation." In International Journal of Advanced Research in Electrical, Electronics and Instrumentation, Vol. 2, Issue 11 [2013]
- D. Kapoor, H. Bangar, Abhishek Chaurasia, and A. Sethi, "An ingenious technique for symbol identification from high noise CAPTCHA images." In India Conference (INDICON), 2012 Annual IEEE, pp. 098-103. IEEE [2012]
- A.K. Mishra, and Abhishek Chaurasia, "Cerebral cortex inspired cognitive architecture for robots." In Energy, Automation, and Signal (ICEAS), 2011 International Conference on, pp. 1-5. IEEE [2011]