Comparison and development of cross-study normalization methods for inter-species transcriptional analysis.

Performing joint analysis of gene expression datasets from different experiments can present challenges brought on by multiple factors-differences in equipment, protocols, climate etc. "Cross-study normalization" is a general term for transformations aimed at eliminating such effects, thus making datasets more comparable. However, joint analysis of datasets from different species is rarely done, and there are no dedicated normalization methods for such inter-species analysis.

Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks.

Graph convolutional networks (GCNs) are widely used in a variety of applications and can be seen as an unstructured version of standard convolutional neural networks (CNNs). As in CNNs, the computational cost of GCNs for large input graphs (such as large point clouds or meshes) can be high and inhibit the use of these networks, especially in environments with low computational resources. To ease these costs, quantization can be applied to GCNs.

GradFreeBits: Gradient-Free Bit Allocation for Mixed-Precision Neural Networks.

Quantized neural networks (QNNs) are among the main approaches for deploying deep neural networks on low-resource edge devices. Training QNNs using different levels of precision throughout the network (mixed-precision quantization) typically achieves superior trade-offs between performance and computational load. However, optimizing the different precision levels of QNNs can be complicated, as the values of the bit allocations are discrete and difficult to differentiate for.

Mimetic Neural Networks: A Unified Framework for Protein Design and Folding.

Recent advancements in machine learning techniques for protein structure prediction motivate better results in its inverse problem-protein design. In this work we introduce a new graph mimetic neural network, MimNet, and show that it is possible to build a reversible architecture that solves the structure and design problems in tandem, allowing to improve protein backbone design when the structure is better estimated. We use the ProteinNet data set and show that the state of the art results in protein design can be met and even improved, given recent architectures for protein folding.