id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-033723-jy5fdsp9	Orhobor, Oghenejokpeme I.	Generating Explainable and Effective Data Descriptors Using Relational Learning: Application to Cancer Biology	2020-09-19		.txt	text/plain	4013	229	52	In many scientific problems explainable models are required, and the input data is semantically complex and unsuitable for DNNs. This is true in the fundamental problem of understanding the mechanism of cancer drugs, which requires complex background knowledge about the functions of genes/proteins, their cells, and the molecular structure of the drugs. This has changed with the success of deep neural-networks (DNNs), which has been based on their capacity to utilize multiple neural network layers, and large amounts of data, to learn how to convert raw propositional descriptors (e.g., image pixel values) into richer internal representations that are effective for learning. We hypothesized that we could improve both ML model explainability, and predictive accuracy, by including additional background knowledge in the learning process using a hybrid RL approach. Furthermore, there exist several other approaches for learning representations from graph or inherently relational data [3, 13] with varying levels of predictive performance and interpretability.	./cache/cord-033723-jy5fdsp9.txt	./txt/cord-033723-jy5fdsp9.txt