no code implementations • MIDL 2019 • Max Blendowski, Mattias P. Heinrich
Current deep learning methods are based on the repeated, expensive application of convolutions with parameter-intensive weight matrices.
1 code implementation • 29 Jan 2018 • Mattias P. Heinrich, Max Blendowski, Ozan Oktay
We propose a new scheme that approximates both trainable weights and neural activations in deep networks by ternary values and tackles the open question of backpropagation when dealing with non-differentiable functions.