11 citations · 42 across the 10 of their papers we have counts for
Showing 2018Show all
2 papers · 1 filter
cs.LG2018
Regularized Binary Network Training
Sajad Darabi, Mouloud Belbahri, Matthieu Courbariaux +1
There is a significant performance gap between Binary Neural Networks (BNNs) and floating point Deep Neural Networks (DNNs). We propose to improve the binary training method, by in…
cs.LG2018
Dynamic Feature Acquisition Using Denoising Autoencoders
Mohammad Kachuee, Sajad Darabi, Babak Moatamed +1
In real-world scenarios, different features have different acquisition costs at test-time which necessitates cost-aware methods to optimize the cost and performance trade-off. This…