1 code implementation • 30 Sep 2022 • Sikun Lin, Thomas Sprague, Ambuj K Singh
Instead of training models from scratch to find a latent space shared by the three modalities, we encode fMRI signals into this pre-aligned latent space.
1 code implementation • 21 Jul 2022 • Ali Borji, Sikun Lin
We show, both theoretically and experimentally, that SplitMixer performs on par with the state-of-the-art MLP-like models while having a significantly lower number of parameters and FLOPS.
1 code implementation • 23 May 2022 • Sikun Lin, Shuyun Tang, Scott Grafton, Ambuj Singh
Finding an appropriate representation of dynamic activities in the brain is crucial for many downstream applications.
no code implementations • 19 Apr 2021 • Hongyuan You, Sikun Lin, Ambuj K. Singh
This not only leads to a cleaner way of applying network constraints but also provides a more scalable solution when network connectivity is sparse.
1 code implementation • ICLR 2020 • Ali Borji, Sikun Lin
A white noise analysis of modern deep neural networks is presented to unveil their biases at the whole network level or the single neuron level.
no code implementations • 22 Feb 2018 • Sikun Lin, Pan Hui
In this work, we present the novel idea of personalized attention prediction and develop Personalized Attention Network (PANet), a convolutional network that predicts saliency in images with personal preference.