Don't want to miss out on the AI wave?
summary
Starts with concrete steps: use Cognitive APIs for vision/speech, then Azure ML Studio drag‑and‑drop, Kaggle notebooks for examples and datasets, and Azure Machine Learning Workbench to run experiments on cloud VMs. Claims data cleaning takes 80% of time; uses a 75/25 split for train/score. Demos show Custom Vision classifying images at nearly 100% probability. Recommends deep learning via Keras with TensorFlow and notes an attempted RNN "self‑clone" project that is not yet working.
AI-written summary · about
chapters (4)
- 0:00Start
- 4:25ML can answer these main types of questions: Classification is this group A, B, C or D? • Anomaly detection is this weird? . Regression - how much? Or how many? Clustering - what patterns are there? . Reinforcement learning - what should I do next?
- 8:02Cognitive APIs • First in class algorithms, prepackaged for you • Leveraging datasets and massive computing power of others Great for learning applications of ML, and fast way to use these in your projects
- 12:57kaggle . Lots of datasets to experiment on (data world is another great source) - Notebooks are your best friend • Participate in challenges!
related talks
57mEasier AI allows everyone to build smart apps
33mApplied AI: Real-world use cases for Microsoft's Azure Cognitive Services
01h 00mLearn Live: Get started with AI on Azure
01h 00m5 Levels of AI in Microsoft Azure
46mBuilding accessible experiences with AI
01h 00mHello AI World! - Why Developers Should Care About AI
58mDeep Learning in Microsoft Azure: CNTK, CaffeOnSpark and Tensorflow
16mHow to get started with Computer Vision AutoML in Azure