3 papers
cs.LG2024
Cost-Effective Attention Mechanisms for Low Resource Settings: Necessity & Sufficiency of Linear Transformations
Peyman Hosseini, Mehran Hosseini, Ignacio Castro +1
From natural language processing to vision, Scaled Dot Product Attention (SDPA) is the backbone of most modern deep learning applications. Unfortunately, its memory and computation…
cs.CV2024
GeoPos: A Minimal Positional Encoding for Enhanced Fine-Grained Details in Image Synthesis Using Convolutional Neural Networks
Mehran Hosseini, Peyman Hosseini
The enduring inability of image generative models to recreate intricate geometric features, such as those present in human hands and fingers has been an ongoing problem in image ge…
cs.CL2023
Lon-ea at SemEval-2023 Task 11: A Comparison of Activation Functions for Soft and Hard Label Prediction
Peyman Hosseini, Mehran Hosseini, Sana Sabah Al-Azzawi +3
We study the influence of different activation functions in the output layer of deep neural network models for soft and hard label prediction in the learning with disagreement task…