1 code implementation • 6 Apr 2023 • Garrett Bingham
While present methods focus on hyperparameters and neural network topologies, other aspects of neural network design can be optimized as well.
2 code implementations • NeurIPS 2023 • Garrett Bingham, Risto Miikkulainen
Second, a characterization of the benchmark space was developed, leading to a new surrogate-based method for optimization.
1 code implementation • 18 Sep 2021 • Garrett Bingham, Risto Miikkulainen
By analytically tracking the mean and variance of signals as they propagate through the network, AutoInit appropriately scales the weights at each layer to avoid exploding or vanishing signals.
no code implementations • 5 Jun 2020 • Garrett Bingham, Risto Miikkulainen
Recent studies have shown that the choice of activation function can significantly affect the performance of deep learning networks.
no code implementations • 17 Feb 2020 • Garrett Bingham, William Macke, Risto Miikkulainen
The choice of activation function can have a large effect on the performance of a neural network.
no code implementations • ACL 2019 • Rui Zhang, Caitlin Westerfield, Sungrok Shim, Garrett Bingham, Alexander Fabbri, Neha Verma, William Hu, Dragomir Radev
In this paper, we propose to boost low-resource cross-lingual document retrieval performance with deep bilingual query-document representations.
Cross-Lingual Information Retrieval Cross-Lingual Word Embeddings +3
no code implementations • 15 Nov 2018 • Benjamin Yip, Garrett Bingham, Katherine Kempfert, Jonathan Fabish, Troy Kling, Cuixian Chen, Yishi Wang
We perform preliminary studies on a large longitudinal face database MORPH-II, which is a benchmark dataset in the field of computer vision and pattern recognition.
no code implementations • 2 Nov 2017 • Garrett Bingham
In this paper, a novel technique named random subspace two-dimensional LDA (RS-2DLDA) is developed for face recognition.