Ankur Mali is an Assistant Professor in the department of computer science and engineering at the University of South Florida. He was awarded Ph.D. in Informatics at Pennsylvania State University in 2022, under Dr. Lee Giles. Before this, he worked in industry and obtained a bachelor’s in Computer Engineering from the University of Pune, India in 2013. He was also awarded prestigious IVADO postdoctoral Fellowship to work with University of Montreal.
At USF, he is the founder and scientific director of the Trustworthy knowledge-driven AI TKAI lab.
- I have broad interests in natural language processing, neuro-symbloic AI and predictive coding. My research is mostly driven by two goals:
- Designing efficient and fundamental approaches to derive knowledge from data and encode human level reasnoning in to intelligents systems.
- Extending such model capabilities to generate interpretable, robust and fair representation.
I believe Neuro-symbolic AI and understanding of complex systems is a crutical steps towards desigining stable Artificial General Intelligence systems.
Formal method meet AI/Neuro-Symbloic AI: My work is at the intersection of language, memory, and computation—spanning Natural Language Processing (NLP), linguistics, and formal language theory. In particular, I design knowledge-guided interpretable deep learning systems focused on generating trustworthy information. Furthermore, I am also interested in investigating the mysterious success of deep learning in recognizing natural language from a theoretical and empirical perspective.
Predictive coding-inspired Neural Architectures: Our lab, in collaboration with NAC, works on designing learning algorithms and computational architectures guided by theories of the brain and its functionality that emphasize solving challenges such as continual/lifelong learning, learning with minimal supervision, Reinforcement Learning, and sparsity (both in computer vision and natural language processing).
Low Resource and Robust NLP: In collaboration with our collaborator from University of Mississippi, we are working on designing low-resource Natural language processing (NLP) agents that are robust and capable of generating safe/ethical information. Such models are aimed to help under-represented groups.
Notes to Prospective Students:
- Job Opening: I am looking for a new Ph.D. student to begin in Spring/Fall 2023. All emails should have the title: Ph.D. Spring/Fall 2023. In brief words, Please provide details about why you wish to join our lab and what topics you wish to work on/explore. Please refer to instructions prior contacting me.
- Students at USF interested in doing an Independent Study or Master’s thesis (seeking me as advisor) should also provide all the details highlighted above.
- Sept 2022: I will be giving a talk on Provable stability of Neural State Turing Machine at RIT
- Sept 2022: I will be giving a talk on Provable stability of Neural State Turing Machine at AI+X Seminar at USF
- Sept 2022: One paper accepted in NeurIPS-22
- Aug 2022: Joined University of South Florida as Assistant Professor (Tenure-Track)
- Mar 2022: Received prestigious IVADO postdoctoral Fellowship (Declined)
- Jan 2022: Received Postdoctoral position at Harvard Medical and Dana-farber cancer center to work on NLP for clinical trials (Declined)
- June 2022: Defended my thesis on Turing Completeness of Neural Networks with bounded precision and time
- Jan 2022: One paper accepted in AAAI-22 (oral) (Backprop free RL).
- Jan 2022: One paper accepted in DCC-22 (Neural JPEG)