Daniel Neil

Position:
PhD Student -- ended May 2017
Email:
Work phone:
Location:

Daniel Neil received his B.S. degree in Biomedical Computation from Stanford and minored there in Chinese and Japanese. He completed his master’s degree in the Neural Systems and Computation program from the Institute of Neuroinformatics and is currently pursuing his Doctoral degree at the INI. Formerly, he was a research assistant in Kwabena Boahen’s Brains in Silicon Laboratory at Stanford and helped to build Neurogrid (the lowest-power neuron supercomputer), and worked as a technical consultant in the San Francisco Bay Area. He is also a co-founder of Ponder (www.pondertalks.com), a site to discover intellectual events.

Currently, his research interests focus on discovering scalable architectures for advanced machine learning, with a focus on deep neural networks. Specifically, he focuses on analyzing and building neuron models and hardware architectures that support efficient processing of deep neural networks, convolutional neural networks, and recurrent neural networks.

Publications

2017

  • Anumula, J., Neil, D., Xiaoya Li, X., Delbruck, T., and Liu, S-C. Live Demonstration: Event-Driven Real-Time Spoken Digit Recognition System, IEEE Int. Symposium on Circuits and Systems (ISCAS), 2017
  • Braun, S., Neil, D., and Liu, S-C. A Curriculum Learning Method for Improved Noise Robustness in Automatic Speech Recognition, 25th European Signal Processing Conference , 2017
  • Neil, D. , Lee, J-H., Delbruck, T. and Liu, S-C. Delta networks for optimized recurrent network computation, Proceedings of the 34th International Conference on Machine Learning, 2017
  • Neil D., Pfeiffer M., and Liu S-C Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences, Proc. of NIPS 2016, 2017

2016

2015

2014

2013

© 2017 Institut für Neuroinformatik