Building Intelligent Mobile Apps using Machine Learning
summary
Walkthrough of how to go from dataset to deployed mobile model using Python and cloud tools, with concrete demos and numbers: data cleaning and k‑means clustering in Jupyter/scikit‑learn, a logistic model trained on an 891-row Titanic dataset vs a second algorithm for accuracy comparison, Azure drag‑and‑drop pipelines with 25 built‑in algorithms, Microsoft Cognitive Services Custom Vision -> Core ML export, training on 19 durian images and installing on an iPhone camera app where the model reliably labels durians in live preview.
AI-written summary · about
chapters (9)
- 0:00Introduction and setup
- 3:21What is machine learning
- 9:28Machine learning applications
- 15:50Supervised vs unsupervised learning
- 26:39Machine learning tools and APIs
- 32:15Azure ML Studio demo
- 39:59Microsoft Cognitive Services
- 45:12Custom Vision and demos
- 49:18Resources and conclusion
related talks
50mBuilding Intelligent Mobile Apps using Machine Learning
53mBuilding Intelligent .NET MAUI Apps with ML.NET
56mBuilding Intelligent Apps with Machine Learning
59mA developers guide to Machine Learning
29mPushing Machine Learning into your app When TensorFlow and MLKit rule the world
27mMachine Learning and Mobile
24mDon't want to miss out on the AI wave?
38mReal Life Customer Stories with AI