Abhijit Mahalunkar

Mutual Information Decay Curves and Hyper-Parameter Grid Search Design for Recurrent Neural Architectures

Dec 08, 2020
Abhijit Mahalunkar, John D. Kelleher

Figure 2 for Mutual Information Decay Curves and Hyper-Parameter Grid Search Design for Recurrent Neural Architectures

Figure 3 for Mutual Information Decay Curves and Hyper-Parameter Grid Search Design for Recurrent Neural Architectures

Figure 4 for Mutual Information Decay Curves and Hyper-Parameter Grid Search Design for Recurrent Neural Architectures

* Published at the 27th International Conference on Neural Information Processing, ICONIP 2020, Bangkok, Thailand, November 18-22, 2020. arXiv admin note: text overlap with arXiv:1810.02966

Access Paper or Ask Questions

Multi-Element Long Distance Dependencies: Using SPk Languages to Explore the Characteristics of Long-Distance Dependencies

Jul 13, 2019
Abhijit Mahalunkar, John D. Kelleher

Figure 2 for Multi-Element Long Distance Dependencies: Using SPk Languages to Explore the Characteristics of Long-Distance Dependencies

Figure 3 for Multi-Element Long Distance Dependencies: Using SPk Languages to Explore the Characteristics of Long-Distance Dependencies

Figure 4 for Multi-Element Long Distance Dependencies: Using SPk Languages to Explore the Characteristics of Long-Distance Dependencies

* To appear in ACL 2019 workshop on Deep Learning and Formal Languages: Building Bridges

Access Paper or Ask Questions

Generating Diverse and Meaningful Captions

Dec 19, 2018
Annika Lindh, Robert J. Ross, Abhijit Mahalunkar, Giancarlo Salton, John D. Kelleher

Figure 2 for Generating Diverse and Meaningful Captions

Figure 3 for Generating Diverse and Meaningful Captions

Figure 4 for Generating Diverse and Meaningful Captions

* Artificial Neural Networks and Machine Learning - ICANN 2018 (pp. 176-187). Springer International Publishing
* Accepted for presentation at The 27th International Conference on Artificial Neural Networks (ICANN 2018)

Access Paper or Ask Questions

Using Regular Languages to Explore the Representational Capacity of Recurrent Neural Architectures

Aug 15, 2018
Abhijit Mahalunkar, John D. Kelleher

Figure 2 for Using Regular Languages to Explore the Representational Capacity of Recurrent Neural Architectures

Figure 3 for Using Regular Languages to Explore the Representational Capacity of Recurrent Neural Architectures

* International Conference of Artificial Neural Networks (ICANN) 2018

Access Paper or Ask Questions