Neda’s Homepage

Research Interests

Neda Tavakoli is a Ph.D. Candidate in Computer Science at Georgia Institute of Technology, advised by Prof. Srinivas Aluru, an internationally well-known leader. She also obtained her Master’s degree in Machine Learning at Georgia Tech in 2020. She is a highly experienced researcher, with a Ph.D. specializing in designing sequential and parallel algorithms for large-scale graph problems. Her work involves creating a mathematical and algorithmic framework to solve multiple NP-hard problems in genome graphs, utilizing programming languages such as C++, Python, and shell script. Additionally, she has extensive knowledge of deep learning frameworks like TensorFlow, PyTorch, and Jax, and has designed and built several platforms and technologies for deep learning models in finance and computational biology. With a comprehensive understanding of ML accelerators such as GPUs in high-performance computing environments, she is highly skilled in using distributed training approaches for deep learning models. She has also actively contributed to the writing and publishing of research papers, many of which have been cited by other researchers, with over 1000 citations to date.

Education

Invited Talks

Approximate Sequence Matching Algorithms to Handle Bounded Number of Errors, International Workshop on String Algorithms in Bioinformatics (StringBio) Slide, Orlando, FL, USA, 2018.

Publications

A. A. Rahsepar*, N. Tavakoli*, G. H. J. Kim, C. Hassani, F. Abtin, A. Bedayat, How AI Responds to Common Lung Cancer Questions: ChatGPT vs Google Bard, Journal of Radiology 2023. (Link) (*equal first author contribution).

N. Tavakoli, D. Gibney, S. Aluru, Haplotype-aware variant selection for genome graphs, Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (ACM-BCB) 2022. (Link) (PDF).

L. F. Gutirrez, N. Tavakoli, S. S. Namini, A. S. Namin, Similarity Analysis of Federal Reserve Statements The Great Recession vs. COVID-19,  SN Business & Economics 2022 (Link).

R. Flores, A. Siami Namin, N. Tavakoli, S. S. Namini, K. S. Jones, Using Experiential Learning to Teach and Learn Digital Forensics: Educator and Student Perspective, Computers and Education Open 2021 (Link).

C. Jain, N. Tavakoli, S. AluruA Variant Selection Framework for Genome Graphs, Accepted to appear in ISMB 2021.

L. F. Gutirrez, N. Tavakoli, S. S. Namini, A. S. Namin,  A Concern Analysis of Federal Reserve Statements The Great Recession vs. COVID-19,  IEEE International Conference on Big Data (Big Data) 2020.

2020.V. Nair, M. Chatterjee, N. Tavakoli, A. S. Namin, C. Snoeyink, Optimizing CNN using fast Fourier Transformation for Object Recognition, 19th IEEE International Conference on Machine Learning and Applications (ICMLA) 2020.

N. Tavakoli, S. Siami‑Namini, M. Adl Khanghah, F. Mirza Soltani, A. Siami Namin, An autoencoder‑based deep learning approach for clustering time series data, Accepted to appear in Springer Nature (SN) Applied Science, 2020. (Link) (PDF)

N. Tavakoli, D. Dai, Y. Chen, A Software-Defined QoS Provisioning Framework for HPC Applications, Accepted to appear in International Journal of Grid and High Performance Computing, 2020. (PDF)

N. Tavakoli, Modeling Genome Data Using Bidirectional LSTM, IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC), Vol. 2, (pp. 183-188), 2019. (Paper)

S. S. Namini, N. Tavakoli, A. S. Namin, The Performance of LSTM and BiLSTM in Forecasting Time Series, The 2nd Workshop on Big Data Engineering and Analytics in Cyber-Physical Systems BigEACPS’19, 2019.

N. Tavakoli, D. Dai, Y. Chen, Client-side Straggler-Aware I/O Scheduler for Object-based Parallel File Systems, Parallel Computing, Elsevier (ParCo), 2019. (Paper)

S. S. Namini, N. Tavakoli, A. S. Namin, A Comparison of ARIMA and LSTM in Forecasting Time Series, International Conference on Machine Learning Application (ICMLA), Orlando, Florida, USA, December 2018. (Link)

S. Hooshmand, N. Tavakoli, P. Abedin, Sharma V. Thankachan, On Computing Average Common Substring Over Run Length Encoded Sequence, Fundamenta Informaticae, 163(3): 267-273 (2018). (Paper)

N. Tavakoli, D. Dai, Y. Chen, A Software-Defined QoS Provisioning Framework for HPC Applications, CoRR abs/1805.06169, 2018. (Paper, PDF)

D. Dai, R. Ross, D. Khaldi, Y. Yan, D. Matthieu, N. Tavakoli, and Y. Chen, Exploiting Locality in Scientific Workflow System: A Cross-Layer Solution, SC Extended Abstract, CoRR abs/1805.06167 (2018). (Paper)

N. Tavakoli, D. Dai, J. Jenkins, P. Carns, R. Ross and Y. Chen, A Software-Defined Approach for QoS Control in High-Performance Computing Storage Systems, SC Extended Abstract CoRR abs/1805.06161 (2018). (Paper)

N. Tavakoli, D. Dai, Y. Chen, Log-Assisted Straggler-Aware I/O Scheduler for High-End Computing, ICPP-W 2016. (Paper)

N. Tavakoli, Networked Markov Chain Influence Model for Providing Cascade-Resilient Interdependent Network, CRA-W, San Francisco, CA, USA, April 2016. [Poster]

Patents

Honors and Awards

Teaching Experiences