The IOP have produced and published two books and two CD-ROMs to support the course. There is one book and CD-ROM for both the AS section of the course and A2 section. The two books supposedly contain all theory and methods that will be required in the exam whilst the CD-ROM offers a more in depth look at every topic as well other resources such as diagrams for show on an interactive whiteboard . The main method of browsing the text and other data on the CD is via the Folio Views software. Also included on the CD are a number of software packages such as Modellus , a package to demonstrate the effects of mathematical models and Worldmaker, a package that can help students model situations and run simulations based on events occurring. The IOP have also created examples using these programmes linked to the course and these are included on the CD and also accessible through the main browser. In addition support materials are provided via. the IoP Advancing Physics website .
This talk will cover best practices in active learning with real-world examples. How search engines use active learning to select the most impactful results to show raters to improve relevance. How self driving car companies can guess the answers and show them to annotators to get a 10x speed up in data collection. This talk will also go over the state of the art of transfer learning. How LSTMs can be trained on one language and applied to another. How image-net was collected and drove the growth of vision algorithms. How neural nets make it easy to fine tune existing algorithms and get great performance with a small amount of training data. This talk will also cover best practices in training data collection. Training data collection strategies are often overlooked but are often the difference between a successful AI deployment and a science experiment.