Semi-supervised classification with stacked autoencoder

US11544529B2 · kind B2 · utility

Assignee

• KONINIKLIJKE PHILIPS N.V. · NL

Inventors

• Reza Ghaeini · Malden, US
• Sheikh Sadid Al Hasan · Cambridge, US
• Oladimeji Feyisetan Farri · Yorktown Heights, US
• Kathy Mi Young Lee · Westford, US
• Vivek Varma Datla · Ashland, US
• Ashequl Qadir · Melrose, US
• Junyi Liu · Nanhu, CN
• Aaditya Prakash · Waltham, US

Key dates

• Filing date: Sep 4, 2017
• Grant date: Jan 3, 2023
• Expiry date: May 3, 2040

Classification

• Technology area (CPC G): Physics
• CPC primary: G16H50/20
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Techniques described herein relate to semi-supervised training and application of stacked autoencoders and other classifiers for predictive and other purposes. In various embodiments, a semi-supervised model (108) may be trained for sentence classification, and may combine what is referred to herein as a “residual stacked de-noising autoencoder” (“RSDA”) (220), which may be unsupervised, with a supervised classifier (218) such as a classification neural network (e.g., a multilayer perceptron, or “MLP”). In various embodiments, the RSDA may be a stacked denoising autoencoder that may or may not include one or more residual connections. If present, the residual connections may help the RSDA “remember” forgotten information across multiple layers. In various embodiments, the semi-supervised model may be trained with unlabeled data (for the RSDA) and labeled data (for the classifier) simultaneously.