no code implementations • 21 May 2018 • Mohammad Ghasemzadeh, Fang Lin, Bita Darvish Rouhani, Farinaz Koushanfar, Ke Huang
The success of deep learning models is heavily tied to the use of massive amount of labeled data and excessively long training time.
no code implementations • ICLR 2018 • Mohammad Ghasemzadeh, Mohammad Samragh, Farinaz Koushanfar
Recent efforts on training light-weight binary neural networks offer promising execution/memory efficiency.
1 code implementation • 3 Nov 2017 • Mohammad Ghasemzadeh, Mohammad Samragh, Farinaz Koushanfar
We show that the state-of-the-art methods for optimizing binary networks accuracy, significantly increase the implementation cost and complexity.