2018/03/25 by Bart Jacobs, Jacobs, Bart, David Sprunger +1
Computer Science · #92B20 (Primary) 18C50 (Secondary) #AI-based Problem Solving and Planning #C.1.3 #F.3.2 #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #acm:18C50 #acm:92B20 #cs.LG #cs.NE #msc:18C50 #msc:92B20
paper · pdf · doi:10.48550/arxiv.1803.09356
arxiv created 2018/03/25 · openalex publication_date 2018/03/25 · arxiv updated 2018/03/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This article studies (multilayer perceptron) neural networks with an emphasis on the transformations involved --- both forward and backward --- in order to develop a semantical/logical perspective that is in line with standard program semantics. The common two-pass neural network training algorithms make this viewpoint particularly fitting. In the forward direction, neural networks act as state transformers. In the reverse direction, however, neural networks change losses of outputs to losses of inputs, thereby acting like a (real-valued) predicate transformer. In this way, backpropagation is functorial by construction, as shown earlier in recent other work. We illustrate this perspective by training a simple instance of a neural network.