3 citations · 4 across the 5 of their papers we have counts for
6 papers
Learning a Sparse Neural Network using IHT
Saeed Damadi, Soroush Zolfaghari, Mahdi Rezaie +1
The core of a good model is in its ability to focus only on important information that reflects the basic patterns and consistencies, thus pulling out a clear, noise-free signal fr…
The Backpropagation algorithm for a math student
Saeed Damadi, Golnaz Moharrer, Mostafa Cham
A Deep Neural Network (DNN) is a composite function of vector-valued functions, and in order to train a DNN, it is necessary to calculate the gradient of the loss function with res…
Convergence of the mini-batch SIHT algorithm
Saeed Damadi, Jinglai Shen
The Iterative Hard Thresholding (IHT) algorithm has been considered extensively as an effective deterministic algorithm for solving sparse optimizations. The IHT algorithm benefits…
Gradient Properties of Hard Thresholding Operator
Saeed Damadi, Jinglai Shen
Sparse optimization receives increasing attention in many applications such as compressed sensing, variable selection in regression problems, and recently neural network compressio…
Amenable Sparse Network Investigator
Saeed Damadi, Erfan Nouri, Hamed Pirsiavash
We present "Amenable Sparse Network Investigator" (ASNI) algorithm that utilizes a novel pruning strategy based on a sigmoid function that induces sparsity level globally over the…
On the Compression of Natural Language Models
Saeed Damadi
Deep neural networks are effective feature extractors but they are prohibitively large for deployment scenarios. Due to the huge number of parameters, interpretability of parameter…