Jan WerthinTowards AIGPT-4 ANew Era of AISummarization of “Sparks of Artificial General Intelligence”5 min read·Apr 17, 2023--1--1
Jan WerthChatGPT, our new stackoverflow?I tested chatGPT to ask for quick coding help5 min read·Dec 20, 2022----
Jan WerthHow to reduce the chance to get targeted using StarlinkЯк зменшити шанс потрапити націлитися за допомогою Starlink2 min read·Mar 4, 2022----
Jan WerthinTowards Data ScienceLSTM for Predictive Maintenance on Pump Sensor DataIn this article, we want to look at some time series analysis to explain the thought process in a predictive maintenance case16 min read·Aug 10, 2021--2--2
Jan WerthinTowards Data ScienceWhen “TOPS” are MisleadingNeural accelerators are often characterized with the performance feature “TOPS” — Trillion operations per second. But that alone is not…11 min read·Apr 26, 2021----
Jan WerthinTowards Data ScienceHow to create a celebrity-look-alike demo and run inference on an NPUFull detailed explanation on how to create, transform, and infer a celebrity-look-alike demo with TensorFlow on an i.MX 8M Plus NPU…14 min read·Dec 9, 2020----
Jan WerthinTowards Data ScienceHow to Create and Tune Your Own, Data Set for Facial Recognition using Neural Networks.Creating a Dataset for Celebrity Comparison with Creative Commons License Images and Tuning the Dataset to Perform Better.6 min read·Nov 30, 2020----
Jan WerthinTowards Data ScienceQuantize Your Deep Learning Model to Run on an NPUPreparing a TensorFlow Model to Run Inference on an i.mx8M Plus NPU6 min read·Nov 16, 2020----
Jan WerthHow to use Keras2 flow_from_directory() with Azure blob storagePreamble9 min read·Jun 17, 2019--2--2