Ashis Kumer Biswas

Ashis Kumer Biswas

Assistant Professor

Posts by Collection

funding

publications

Khaled, S. M. and Biswas, A. K. and Rahman, M. L. and Pervin, S. (2005) An Analysis on Human Resource Development in the ICT Sector of Bangladesh. In the 8th International Conference on Computer & Information Technology, Dec. 28–30, 2005, pp. 507–512.
Khaled, S. M. and Biswas, A. K. and Qayum, M. A. and Rahman, M. L. (2006) Present Status of Telecommunication in Bangladesh and its Impact on ICT. In The 9th International Conference on Computer & Information Technology, Dec. 21–23, 2006, pp. 221–226.
Khaled, S. M., Karim, R., Biswas, A. K., Rahman, R. H., Nowsheen, N., & Qayum, M. A. (2007). Optimization of Reliability in a Real Time Security System Controlled by Embedded Internet Technology. Asian Journal of Information Technology, 6(10), 1050-1056.
Biswas, A. K., Hasan, M. M., Chowdhury, A. R., & Babu, H. M. H. (2008). Efficient approaches for designing reversible binary coded decimal adders. Microelectronics journal, 39(12), 1693-1703.
Biswas, A. K., Hasan, M. M., Hasan, M., Chowdhury, A. R., & Babu, H. M. H. (2008, January). A novel approach to design BCD adder and carry skip BCD adder. In 21st international conference on VLSI design (VLSID 2008) (pp. 566-571). IEEE.
Biswas, A. K., Noman, N., & Sikder, A. R. (2010). Machine learning approach to predict protein phosphorylation sites by incorporating evolutionary information. BMC bioinformatics, 11(1), 1-17.
Biswas, A. K., Jamal, L., Mottalib, M. A., & Babu, H. M. H. (2011). Design of a reversible parallel loading shift register. Dhaka Univ. J. Eng & Tech, 1(2), 1-5.
Sultana, A., Hasan, Q. M., Biswas, A. K., Das, S., Rahman, H., Ding, C., & Li, C. (2012, October). Infobox suggestion for Wikipedia entities. In Proceedings of the 21st ACM international conference on Information and knowledge management (pp. 2307-2310)
Biswas, A. K., Zhang, B., Wu, X., & Gao, J. X. (2013, November). QLZCClust: Quaternary lempel-Ziv complexity based clustering of the RNA-seq read block segments. In 13th IEEE International Conference on BioInformatics and BioEngineering (pp. 1-4). IEEE.
Biswas, A. K. and Gao, J. X. annd Wu, X. and Zhang, B. (2013) Integrating RNA-seq transcript signals, Primary and Secondary Structure Information in Differentiating coding and non-coding RNA transcripts. In The 5th International Conference on Bioinformatics and Computational Biology. ISCA, Mar. 4–6, 2013.
Biswas, A. K., Zhang, B., Wu, X., & Gao, J. X. (2013). CNCTDiscriminator: coding and noncoding transcript discriminator—an excursion through hypothesis learning and ensemble learning approaches. Journal of bioinformatics and computational biology, 11(05), 1342002.
Biswas, A. K., Zhang, B., Wu, X., & Gao, J. X. (2014). An Information Integration Approach for Classifying Coding and Non-Coding Genomic Data. In The Proceedings of the Second International Conference on Communications, Signal Processing, and Systems (pp. 1085-1093). Springer, Cham.
Biswas, A. K., Gao, J. X., Zhang, B., & Wu, X. (2014, November). NMF-based LncRNA-disease association inference and Bi-clustering. In 2014 IEEE International Conference on Bioinformatics and Bioengineering (pp. 97-104). IEEE.
Kang, M., Park, J., Kim, D. C., Biswas, A. K., Liu, C., & Gao, J. (2015, November). An integrative genomic study for multimodal genomic data using multi-block bipartite graph. In 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 563-568). IEEE.
Kim, D. C., Kang, M., Biswas, A., Liu, C., & Gao, J. (2015, November). Integrative approach for inference of gene regulatory networks using lasso-based random featuring and application to Psychiatric disorders. In Proceedings of the 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 145-150).
Biswas, A. K., Zhang, B., Wu, X., & Gao, J. X. (2015). A multi-label classification framework to predict disease associations of long non-coding RNAs (lncRNAs). In The Proceedings of the Third International Conference on Communications, Signal Processing, and Systems (pp. 821-830). Springer, Cham.
Biswas, A. K., Kang, M., Kim, D. C., Ding, C. H., Zhang, B., Wu, X., & Gao, J. X. (2015). Inferring disease associations of the long non-coding RNAs through non-negative matrix factorization. Network Modeling Analysis in Health Informatics and Bioinformatics, 4(1), 1-17.
Biswas, A. K., Kim, D. C., Kang, M., & Gao, J. X. (2016, December). Robust Inductive Matrix Completion strategy to explore associations between lincRNAs and human disease phenotypes. In 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 334-339). IEEE Computer Society.
Biswas, A. K., Zhang, B., Wu, X., & Gao, J. X. (2016). Improving Consensus Hierarchical Clustering Framework. In Proceedings of the 2015 International Conference on Communications, Signal Processing, and Systems (pp. 781-791). Springer, Berlin, Heidelberg.
Kim, D., Kang, M., Biswas, A., Liu, C., & Gao, J. (2016). Integrative approach for inference of gene regulatory networks using lasso-based random featuring and application to psychiatric disorders. BMC Medical Genomics, 9(2), 111-122.
Sworna, Z. T., UlHaque, M., Tara, N., Hasan Babu, H. M., & Biswas, A. K. (2016). Low‐power and area efficient binary coded decimal adder design using a look up table‐based field programmable gate array. IET Circuits, Devices & Systems, 10(3), 163-172.
Biswas, A. K., & Gao, J. X. (2016). PR2S2Clust: patched rna-seq read segments’ structure-oriented clustering. Journal of Bioinformatics and Computational Biology, 14(05), 1650027.
Kang, M., Park, J., Kim, D. C., Biswas, A. K., Liu, C., & Gao, J. (2016). Multi-block bipartite graph for integrative genomic analysis. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 14(6), 1350-1358.
Sworna, Z. T., Haque, M. U., Babu, H. M. H., Jamal, L., & Biswas, A. K. (2017, July). An Efficient Design of an FPGA-Based Multiplier Using LUT Merging Theorem. In 2017 IEEE Computer Society Annual Symposium on VLSI (ISVLSI) (pp. 116-121). IEEE.
Biswas, A., & Gao, J. (2017, November). LiDiAimc: LincRNA-disease associations through inductive matrix completion. In 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 158-163). IEEE.
Babu, H. M. H., Jamal, L., Dibbo, S. V., & Biswas, A. K. (2017, July). Area and delay efficient design of a quantum bit string comparator. In 2017 IEEE Computer Society Annual Symposium on VLSI (ISVLSI) (pp. 51-56). IEEE.
Biswas, A. K., Kim, D., Kang, M., Ding, C., & Gao, J. X. (2017). Stable solution to l 2, 1-based robust inductive matrix completion and its application in linking long noncoding RNAs to human diseases. BMC Medical Genomics, 10(5), 1-16. Chicago.
Kim, D. C., Kang, M., Biswas, A., Yang, C. R., Wang, X., & Gao, J. X. (2017). Effects of low dose ionizing radiation on DNA damage-caused pathways by reverse-phase protein array and Bayesian networks. Journal of Bioinformatics and Computational Biology, 15(02), 1750006.
Babu, H. M., Mia, M., & Biswas, A. K. (2017). Efficient techniques for fault detection and correction of reversible circuits. Journal of Electronic Testing, 33(5), 591-605.
H. Holme and A. K. Biswas. (2018) Toward pre-pregnancy diagnosis of autism spectrum disorders using machine learning algorithms, in Workshop on Human and Mammalian Genetics and Genomics and the 59th McKusick Short Course. Jackson Laboratory, Bar Harbor, Maine, 2018, pp. 1–1.
Debnath, M., Tripathi, P. K., Biswas, A. K., & Elmasri, R. (2018, November). Preference aware travel route recommendation with temporal influence. In Proceedings of the 2nd ACM SIGSPATIAL Workshop on Recommendations for Location-based Services and Social Networks (pp. 1-9).
Ul Haque, M., Sworna, Z. T., Hasan Babu, H. M., & Biswas, A. K. (2018). A fast fpga-based bcd adder. Circuits, Systems, and Signal Processing, 37(10), 4384-4408.
Biswas, A. K., Kim, D. C., Kang, M., & Gao, J. X. (2018). Robust inductive matrix completion strategy to explore associations between lincrnas and human disease phenotypes. IEEE/ACM transactions on computational biology and bioinformatics, 16(6), 2066-2077.
Pastorino, J., & Biswas, A. K. (2019, November). TexAnASD: Text Analytics for ASD Risk Gene Predictions. In 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 1350-1357). IEEE.
Kang, M., Biswas, A., Kim, D. C., & Gao, J. (2019, December). Semi-Supervised Discriminative Transfer Learning in Cross-Language Text Classification. In 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) (pp. 1031-1038). IEEE.
Peng, J., Debnath, M., & Biswas, A. K. (2021). Efficacy of novel Summation-based Synergetic Artificial Neural Network in ADHD diagnosis. Machine Learning with Applications, 6, 100120.
Biswas, A. K. and Sikder, A. R. and Noman, N. (2010) Incorporating Evolutionary Information in Protein Phosphorylation Site Predictions. In The 8th Asia Pacific Bioinformatics Conference. ISCB, Jan. 18–21.
Pastorino, J., & Biswas, A. K. (2020, December). Hey ML, what can you do for me?. In 2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE) (pp. 116-119). IEEE.
Jafarian, J. H., Dincelli, E., Guzik, K., Michaelis, M., Banaei-Kashani, F., & Biswas, A. (2020). Deception against Deception: Toward A Deception Framework for Detection and Characterization of Covert Micro-targeting Campaigns on Online Social Networks. In Workshop on Information Security and Privacy (WISP)
Bekman, T., Abolfathi, M., Jafarian, H., Biswas, A., Banaei-Kashani, F., & Das, K. (2021, September). Practical Black Box Model Inversion Attacks Against Neural Nets. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (pp. 39-54). Springer, Cham.
Biswas, A. K., Verma, G., & Barber, J. O. (2021). Improving Ethical Outcomes with Machine-in-the-Loop: Broadening Human Understanding of Data Annotations. arXiv preprint arXiv:2112.09738.
Pastorino, J., Director, J. W., Biswas, A. K., & Hawbaker, T. J. (2022, April). Determination of optimal set of spatio-temporal features for predicting burn probability in the state of California, USA. In Proceedings of the 2022 ACM Southeast Conference (pp. 151-158).
Michaelis, M., Jafarian, J. H., & Biswas, A. (2022, June). The Dangers of Money and Corporate Power Relating to Online Disinformation. In 2022 23rd IEEE International Conference on Mobile Data Management (MDM) (pp. 470-475). IEEE.
Pastorino, J., & Biswas, A. K. (2022, August). Data adequacy bias impact in a data-blinded semi-supervised GAN for privacy-aware COVID-19 chest X-ray classification. In Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (pp. 1-8).
Mehrpour, O., Hoyte, C., Delva‐Clark, H., Al Masud, A., Biswas, A., Schimmel, J., ... & Goss, F. (2022). Classification of acute poisoning exposures with machine learning models derived from the National Poison Data System. Basic & Clinical Pharmacology & Toxicology, 131(6), 566-574.
Verma, G., Campbell, T., Biswas, A., Riley, J., Browning-Caraballo, T., Puvirajah, A. (2023, April). Informal STEM learning opportunities: Artificial intelligence and micro credentialing as a tool to recognize and develop Teens' STEM Identities. Presented as Poster in the Research in Artificial Intelligence-involved Science Education (RAISE) RIG at the 96th National Association for Research in Science Teaching (NARST) Annual Conference. Chicago, IL.
Mehrpour, O., Hoyte, C., Al Masud, A., Biswas, A., Schimmel, J., Nakhaee, S., ... & Goss, F. (2023). Deep learning neural network derivation and testing to distinguish acute poisonings. Expert Opinion on Drug Metabolism & Toxicology, 19(6), 367-380.

talks

Characterizing brain tumor subtypes from MRI images – a computational approach

Brain tumors are the second most common malignancy in childhood after leukemia. Magnetic resonance imaging (MRI) is a popular clinical method to diagnose brain tumors due to the fact that it is a non-invasive, painless procedure without any ionizing radiation. The standard pipeline for diagnosis after generating MRI scans require clinicians’ expert examination to pinpoint location, size, and types of brain tumor. To assist in the examination, there are also several proprietary tools exist that offer basic image analysis, including segmentation based on histograms, etc. Automated secondary analysis on the images is still performed manually by a clinician. There is a need to develop a tool to help reducing clinicians’ average investigation time on an image by developing a prediction algorithm leveraging the power of the deep neural network to determine the four subtypes of brain tumor: medulloblastomas, DIPG, ependymomas, and edema.

Artificial Intelligence and its key contributions in the medical imaging field

Driven by the combination of easy, inexpensive access to huge volume of data, computational infrastructure and advanced algorithms, Artificial Intelligence (AI) has entered into the mainstream of technological innovations including machine learning, deep learning, natural language processing, robotics, and image data analysis which are not only helping us to live and maintain an improved lifestyle 24/7, but also are being the key contributors in the achievement of many of the recent notable scientific works in health science. One of the most impactful areas of health innovations is the application of AI in medical imaging. In this talk, recent advancements of AI will be introduced including automated image processing and interpretations of the analysis. Basic terminologies commonly used while discussing AI applications will be explained with illustrations, and finally the three questions around the “when”, “what” and “how” AI can be integrated into a medical imaging (more specifically radiological) workflow will be illustrated with examples.

Data Science Competitions: A know-how to participate

It is problematic to find that there is a skewed availability of data science related learning contents vs. contents leading to what one is supposed to do with the learned concepts. Most teaching materials in Data Science, especially, Machine Learning and Deep Learning in an academic setting struggle to engage the pupils in applying the knowledge to solve everyday problems. There is a “believable gap” between graduating from a relevant course and applying the learned ideas in a real world impactful problem solving. Participating at the competitive data science platforms like Kaggle, DrivenData etc. put a participant in a position to utilize the concepts in a more practical way which is both encouraging and constructive. In this talk, the audience will learn about the importance of participating at the competitions, how to start participating at one of the venue, Kaggle and possessing a competitive mindset to improve the submission entry little-by-little amongst the thousands of experts in the world and eventually become successful in their career in Data Science.

Data-blind Machine Learning:– only a piece of puzzle building models in oblivious settings

Supervised machine learning models are, by definition, data-sighted, requiring to view all or most parts of the training dataset which are labeled. This paradigm presents two bottlenecks which are intertwined: risk of exposing sensitive data samples to the third-party site with machine learning engineers, and time-consuming, laborious, bias-prone nature of data annotations by the personnel at the data source site. In this paper we studied learning impact of data adequacy as bias source in a data-blinded semi-supervised learning model for covid chest X-ray classification. Data-blindedness was put in action on a semi-supervised generative adversarial network to generate synthetic data based only on a few labeled data samples and concurrently learn to classify targets. We designed and developed a data-blind COVID–19 patient classifier that classifies whether an individual is suffering from COVID–19 or other type of illness with the ultimate goal of producing a system to assist in labeling large datasets. However, the availability of the labels in the training data had an impact in the model performance, and when a new disease spreads, as it was COVID9-19 in 2019, access to labeled data may be limited. Here, we studied how bias in the labeled sample distribution per class impacted in classification performance for three models: a Convolution Neural Network based classifier (CNN), a semi-supervised GAN using the source data (SGAN), and finally our proposed data-blinded semi-supervised GAN (BSGAN). Data-blind prevents machine learning engineers from directly accessing the source data during training, thereby ensuring data confidentiality. This was achieved by using synthetic data samples, generated by a separate generative model which were then used to train the proposed model. Our model achieved comparable performance, with the trade–off between a privacy–aware model and a traditionally–learnt model of $0.05$ AUC–score, and it maintained stable, following the same learning performance as the data distribution was changed.

Responsible AI Practices

The fourth industrial revolution fuses Artificial Intelligence (AI) into the advancement of automation technologies from numerous disciplines, thereby impacting various aspects of people’s lives and the society at large. It is, therefore, important to design, build and deploy AI systems responsibly to ensure fairness, inclusiveness, reliability, transparency, privacy, accountability and understanding of limitations. The talk illustrates the responsible AI system design principles and the “think-before-you-code” practices to make an impact.

teaching

CSCI-2312: Object Oriented Programming

Undergraduate course, PLAZA-112, 2017

Programming topics in the C++ language. The emphasis is on problem solving using object oriented and Generic Programming. Topics include advanced I/O, classes, inheritance, polymorphism and virtual functions, abstract base classes, exception handling, templates, and the Standard Template Library.

CSCI-5800: Machine Learning

Cross-listed course (ugrad+grad), Lawrence Street Center - 840, 2018

Welcome to Machine learning course. What is machine learning? It is concerned with the question of how to write computer programs that automatically improve with experience. The field has expanded so much in every direction of our daily lives that we mostly are unaware of its presence. Interestingly, there may be two perspectives to this oblivion. First one is that the machine learning applications have greatly improved themselves over time and became part of your lifestyle. However, a completely opposite perspective is that we became part of it, and unknowingly feeding input to the program as if we are in a computer simulation? In this class, you will learn about machine learning, its application in diverse domains, get to implement them yourself and raise awareness of its presence and associated implications in our day-to-day lives. Once again welcome aboard.

CSCI-5800: Deep Learning

Cross-listed (Grad+UGrad) course, CU BLDG 470, 2018

Welcome to Deep learning course. What is Deep learning? It is actually a subfeld of machine learning mostly concerned with concepts and techniques built on top of the artifcial neural networi which in turn was inspired by the structure and functionality of human brain. This branch of machine learning is increasingly gaining popularity as deep learning systems are taiing over all artifcial intelligent tasis, ranging from image classifcation, language modeling, machine translation,cplaying games, autonomous vehicle driving, speech recognition, cancer detection and numerous other applications and dominating over most competing systems. In this course you will gain both theoretical and practical inowledge of deep learning concepts and techniques. So, welcome aboard!

CSCI-4930/5930: Machine Learning

Cross-listed course (ugrad+grad), Student Commons -2504, 2019

Welcome to Machine learning course. What is machine learning? It is concerned with the question of how to write computer programs that automatically improve with experience. Over the very recent years, the field has expanded so much in every direction of our daily lives that we mostly are unaware of its existence. But, as a concerned citizen of the world, we are going to know the nuts and bolts of machine learning.

CSCI-4931/5931: Deep Learning

Cross-listed (Grad+UGrad) course, NORTH 1003, 2019

Deep Learning is a subfield of machine learning mostly concerned with concepts and techniques built on top of the artificial neural network which in turn was inspired by the structure and functionality of human brains. This branch of machine learning is increasingly gaining popularity as deep learning systems are taking over all artificial intelligent tasks, ranging from image classification, language modeling, machine translation, playing games, autonomous vehicle driving, speech recognition, cancer detection and numerous other applications and is behind many recent advances in Artificial Intelligence (AI). In this course you will gain both theoretical and practical knowledge of deep learning concepts and techniques. So, welcome aboard!

CSCI-4930/5930: Machine Learning

Cross-listed course (ugrad+grad), Student Commons -1500+ Remote, 2020

Welcome to Machine learning course. What is machine learning? It is concerned with the question of how to write computer programs that automatically improve with experience. Over the very recent years, the field has expanded so much in every direction of our daily lives that we mostly are unaware of its existence. But, as a concerned citizen of the world, we are going to know the nuts and bolts of machine learning.

CSCI-4800/5800: Bioinformatics

Cross-listed (UGrad+Grad) course, Remote, 2020

Biological sciences are undergoing a revolution in how they are practiced. In the last decade, a vast amount of data (Electronic Health Records (EHR), DNA sequences, protein sequences, etc.) has become available, and computational methods are playing a fundamental role in transforming this data into scientific understanding. Bioinformatics involves developing and applying computational methods for managing and analyzing information about the clinical, sequence, structure and function of biological molecules and systems. Topics will include understanding the evolutionary organization of genes (genomics), the structure and function of gene products (proteomics), the dynamics for gene expression in biological processes (transcriptomics), and other omics data including tumor tissue imaging, MRIs, EEG, ECG, and numerous human diseases and disorders. Students will also learn about the technology behind the Next Generation Sequencing (NGS), also known as the High Throughput Sequencing (HTS), Genome Wide Association Studies (GWAS) and get skills to analyze associated datasets to decipher useful information.

CSCI-4800/5800: AI with Reinforcement Learning

Cross-listed (UGrad+Grad) course, Remote, 2020

We now live in an era of Artificial Intelligence (AI) where we rely on responses as well as actions by numerous autonomous systems that are crisscrossed in our daily lives. These systems are powered by AI that learn to provide us with reasonable answers for us with respect to our respective perspectives. Reinforcement learning is one of the most advanced and powerful way of developing such systems and are very much in line with the learning paradigms used to make us knowledgeable since our childhood, which is to learn from our mistakes. In this course, students are going to get a solid foundation in the field of reinforcement learning, learn the core challenges, and ideas to bring in newer approaches to make the systems robust, and more humanoid, and better to some degree. Through a combination of lectures, programming assignments students are expected to receive a hands-on-experience in exploring this field effectively. In addition, through the final project in this course, students will advance their understanding of reinforcement learning paradigm and are going to be able to design, develop and demonstrate by the end of the semester smart competitive players in video games, autonomous chatbots, autonomous vehicle control systems, early detection of malicious activities in the communication networks in the field of cybersecurity, and so on.

CSCI-4931/5931: Deep Learning

Cross-listed (Grad+UGrad) course, Remote, 2021

Deep Learning is a subfield of machine learning mostly concerned with concepts and techniques built on top of the artificial neural network which in turn was inspired by the structure and functionality of human brains. This branch of machine learning is increasingly gaining popularity as deep learning systems are taking over all artificial intelligent tasks, ranging from image classification, language modeling, machine translation, playing games, autonomous vehicle driving, speech recognition, cancer detection and numerous other applications and is behind many recent advances in Artificial Intelligence (AI). In this course you will gain both theoretical and practical knowledge of deep learning concepts and techniques. So, welcome aboard!

CSCI-4930/5930: Machine Learning

Cross-listed course (ugrad+grad), NORTH-1005, 2021

Welcome to Machine learning course. What is machine learning? It is concerned with the question of how to write computer programs that automatically improve with experience. Over the very recent years, the field has expanded so much in every direction of our daily lives that we mostly are unaware of its existence. But, as a concerned citizen of the world, we are going to know the nuts and bolts of machine learning.

CSCI-2312: Object Oriented Programming

Undergraduate course, NORTH-1005, 2021

Programming topics in a modern programming language. Student will be introduced to an object oriented programming language. The emphasis is on problem solving using object oriented and generic programming. Topics includes classes, inheritance, polymorphism, virtual functions, abstract classes, exception handling, templates, and the Standard Template Library.

CSCI-3412: Algorithm

Undergraduate course, KING-312, 2022

Design and analysis of algorithms. Asymptotic analysis as a means of evaluating algorithm efficiency. The application of induction and other mathematical techniques for proving the correctness of an algorithm. Data structures for simplifying algorithm design, such as hash tables, heaps and search trees. Elementary graph algorithms. Assignments include written work and programming assignments.

CSCI-5931: Deep Learning

Graduate course, Online, 2022

Deep Learning is a subfield of machine learning mostly concerned with concepts and techniques built on top of the artificial neural network which in turn was inspired by the structure and functionality of human brains. This branch of machine learning is increasingly gaining popularity as deep learning systems are taking over all artificial intelligent tasks, ranging from image classification, language modeling, machine translation, playing games, autonomous vehicle driving, speech recognition, cancer detection and numerous other applications and is behind many recent advances in Artificial Intelligence (AI). In this course you will gain both theoretical and practical knowledge of deep learning concepts and techniques. So, welcome aboard!

CSCI-4930: Machine Learning

Undergraduate course, LSC-836 (Tue) + online, 2022

Welcome to Machine learning course. What is machine learning? It is concerned with the question of how to write computer programs that automatically improve with experience. Over the very recent years, the field has expanded so much in every direction of our daily lives that we mostly are unaware of its existence. But, as a concerned citizen of the world, we are going to know the nuts and bolts of machine learning.

CSCI-5930: Machine Learning

Graduate course, SCB-2500A (Tue only) + Online, 2022

Welcome to Machine learning course. What is machine learning? It is concerned with the question of how to write computer programs that automatically improve with experience. Over the very recent years, the field has expanded so much in every direction of our daily lives that we mostly are unaware of its existence. But, as a concerned citizen of the world, we are going to know the nuts and bolts of machine learning.

CSCI-5931: Deep Learning

Graduate course, NORTH-3205 (Tue only) + Online async, 2023

Deep Learning is a subfield of machine learning mostly concerned with concepts and techniques built on top of the artificial neural network which in turn was inspired by the structure and functionality of human brains. This branch of machine learning is increasingly gaining popularity as deep learning systems are taking over all artificial intelligent tasks, ranging from image classification, language modeling, machine translation, playing games, autonomous vehicle driving, speech recognition, cancer detection and numerous other applications and is behind many recent advances in Artificial Intelligence (AI). In this course you will gain both theoretical and practical knowledge of deep learning concepts and techniques. So, welcome aboard!

CSCI-4800/5800: AI with Reinforcement Learning

Graduate course, SCIENCE-1067 (Tue only) + Online async, 2023

We now live in an era of Artificial Intelligence (AI) where we rely on responses as well as actions by numerous autonomous systems that are crisscrossed in our daily lives. These systems are powered by AI that learn to provide us with reasonable answers for us with respect to our respective perspectives. Reinforcement learning is one of the most advanced and powerful way of developing such systems and are very much in line with the learning paradigms used to make us knowledgeable since our childhood, which is to learn from our mistakes. In this course, students are going to get a solid foundation in the field of reinforcement learning, learn the core challenges, and ideas to bring in newer approaches to make the systems robust, and more humanoid, and better to some degree. Through a combination of lectures, programming assignments students are expected to receive a hands-on-experience in exploring this field effectively. In addition, through the final project in this course, students will advance their understanding of reinforcement learning paradigm and are going to be able to design, develop and demonstrate by the end of the semester smart competitive players in video games, autonomous chatbots, autonomous vehicle control systems, early detection of malicious activities in the communication networks in the field of cybersecurity, and so on.

(Fall’23): CSCI-4931 Deep Learning

Undergraduate course, SCIENCE-2001 (Tue only), 2023

Deep Learning is a subfield of machine learning mostly concerned with concepts and techniques built on top of the artificial neural network which in turn was inspired by the structure and functionality of human brains. This branch of machine learning is increasingly gaining popularity as deep learning systems are taking over all artificial intelligent tasks, ranging from image classification, language modeling, machine translation, playing games, autonomous vehicle driving, speech recognition, cancer detection and numerous other applications and is behind many recent advances in Artificial Intelligence (AI). In this course you will gain both theoretical and practical knowledge of deep learning concepts and techniques. So, welcome aboard!

(Fall’23): CSCI-5930 Machine Learning

Graduate course, SCIENCE-2001 (Tue only), 2023

Welcome to Machine learning course. What is machine learning? It is concerned with the question of how to write computer programs that automatically improve with experience. Over the very recent years, the field has expanded so much in every direction of our daily lives that we mostly are unaware of its existence. But, as a concerned citizen of the world, we are going to know the nuts and bolts of machine learning.

(Spring’24): CSCI-5931 Deep Learning (Online only)

Graduate course, Onlne only, 2024

Deep Learning is a subfield of machine learning mostly concerned with concepts and techniques built on top of the artificial neural network which in turn was inspired by the structure and functionality of human brains. This branch of machine learning is increasingly gaining popularity as deep learning systems are taking over all artificial intelligent tasks, ranging from image classification, language modeling, machine translation, playing games, autonomous vehicle driving, speech recognition, cancer detection and numerous other applications and is behind many recent advances in Artificial Intelligence (AI). In this course you will gain both theoretical and practical knowledge of deep learning concepts and techniques. So, welcome aboard!