Harald ScheidlWhy pooling layers in deep learning can cause problemsPooling layers are omnipresent in today’s computer vision deep learning models. They reduce the size of the feature maps from layer to…7 min read·Jul 21, 2022----
Harald ScheidlinTowards Data ScienceAdaHessian: a second order optimizer for deep learningMost of the optimizers used in deep learning are (stochastic) gradient descent methods. They only consider the gradient of the loss…·6 min read·Aug 9, 2021--1--1
Harald ScheidlDoes padding matter in deep learning models?The article presents two experiments that show the influence of padding in deep learning models.4 min read·Mar 24, 2021--1--1
Harald ScheidlinTowards Data ScienceWhat a text recognition system actually seesSome insights into the neural network “black box” of a text recognition system6 min read·Jan 5, 2019--9--9
Harald ScheidlinTowards Data ScienceGPU Image Processing using OpenCLImplementation of two image processing methods in less than 120 lines of code using Python and OpenCL.·10 min read·Oct 29, 2018--2--2
Harald ScheidlinTowards Data ScienceFAQ: Build a Handwritten Text Recognition System using TensorFlow·5 min read·Sep 13, 2018--22--22
Harald ScheidlinTowards Data ScienceWord Beam Search: A CTC Decoding AlgorithmImprove text recognition results: avoid spelling mistakes, allow arbitrary numbers and punctuation marks and make use of a word-level…·7 min read·Jul 19, 2018--13--13
Harald ScheidlinTowards Data ScienceBeam Search Decoding in CTC-trained Neural NetworksA fast and well-performing algorithm with integrated language model to decode the neural network output in the context of text recognition·9 min read·Jul 10, 2018--8--8
Harald ScheidlinTowards Data ScienceBuild a Handwritten Text Recognition System using TensorFlow·8 min read·Jun 15, 2018--67--67