no code implementations • 23 Sep 2020 • Najeeb Khan, Ian Stavness
However, the huge size of contemporary models results in large inference costs and limits their use on resource-limited devices.
1 code implementation • 17 Apr 2019 • Najeeb Khan, Ian Stavness
We found that sparsity of the activations is favorable for language modelling performance while image classification benefits from denser activations.
no code implementations • 28 May 2018 • Najeeb Khan
In many practical optimization problems, the derivatives of the functions to be optimized are unavailable or unreliable.
no code implementations • 21 Apr 2018 • Najeeb Khan, Jawad Shah, Ian Stavness
Stochastic methods such as Dropout and Shakeout, in expectation, are equivalent to imposing a ridge and elastic-net penalty on the model parameters, respectively.
no code implementations • 13 Jun 2017 • Najeeb Khan, Ian Stavness
In this work, we investigate deep autoencoders for the prediction of muscle activation trajectories for point-to-point reaching movements.