[2U4-IS-2c] Machine learning

[2U4-IS-2c-01] Hybrid models combining neural networks (NN), Gaussian process regressions (GPR), and high-dimensional model representations (HDMR) for more powerful machine learning

We show how using staple techniques such as NN or GPR as building blocks of a more involved method can enhance ML capabilities in high dimension and or with sparse data

〇Sergei Manzhos¹, Shunsaku Tsuda¹, Hyojae Lee¹, Manabu Ihara¹ (1. Tokyo Institute of Technology)

[[Online, Regular]]

キーワード：high-dimensional model representation, neural network , Gaussian process regression

Machine learning (ML) techniques such as neural networks (NN) and Gaussian process regressions (GPR) are now widely used in diverse applications. While each technique has pros and cons, they are all challenged when faced with high dimensionality of the feature space or low and uneven data density. We will demonstrate how combining them with high-dimensional model representations (HDMR) results in methods better apt to deal with these issues. HDMR-NN, HDMR-GPR combinations and NN with HDMR-GPR neuron activation functions will be presented with examples ranging from computational chemistry to quantitative finance.