Search Results for author:
Found 9 papers, 2 papers with code
Towards Understanding Gradient Flow Dynamics of Homogeneous Neural Networks Beyond the Origin
Recent works exploring the training dynamics of homogeneous neural network weights under gradient flow with small initialization have established that in the early stages of training, the weights remain small and near the origin, but converge in direction.
Early Directional Convergence in Deep Homogeneous Neural Networks for Small Initializations
This paper studies the gradient flow dynamics that arise when training deep homogeneous neural networks assumed to have locally Lipschitz gradients and an order of homogeneity strictly greater than two.
Directional Convergence Near Small Initializations and Saddles in Two-Homogeneous Neural Networks
This paper examines gradient flow dynamics of two-homogeneous neural networks for small initializations, where all weights are initialized near the origin.
CLEVR\_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images
Most existing research on visual question answering (VQA) is limited to information explicitly present in an image or a video.
CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images
Most existing research on visual question answering (VQA) is limited to information explicitly present in an image or a video.
Understanding the Role of Scene Graphs in Visual Question Answering
Visual Question Answering (VQA) is of tremendous interest to the research community with important applications such as aiding visually impaired users and image-based search.
Low temperature carrier transport mechanism and photoconductivity of WSe2
The electrical conductivity analysis shows the presence of the three regions with temperature variation.
Materials Science
Convexifying Sparse Interpolation with Infinitely Wide Neural Networks: An Atomic Norm Approach
This work examines the problem of exact data interpolation via sparse (neuron count), infinitely wide, single hidden layer neural networks with leaky rectified linear unit activations.
