Presented by:
Jadga works on Snap! and loves to create fun projects that might also be helpful for students and teachers. Her favourite Snap! block is map <3
Jens Mönig
Jens Mönig is a researcher at SAP and makes interactive programming environments. He is fanatical about visual coding blocks. Jens is the architect and lead programmer of UC Berkeley’s "Snap! Build Your Own Blocks" programming language, used in the introductory “Beauty and Joy of Computing” curriculum. Previously Jens has worked under Alan Kay on the GP programming language together with John Maloney and Yoshiki Ohshima, helped develop Scratch for the MIT Media Lab and written enterprise software at MioSoft. Jens is a fully qualified lawyer in Germany and has been an attorney, corporate counsel and lecturer for many years before rediscovering his love for programming through Scratch and Squeak. For leisure Jens likes guitar picking and strumming his mandolin.
No materials for the event yet, sorry!
Neural networks and deep learning are an important part of current artificial intelligence. Therefore, we want people to understand what's happening under the hood. We've used a single ‘layer’ sprite to create a classic Rosenblatt perceptron. Duplicate the layer sprite multiple times and customise the receivers in the transmission blocks to create deep neural networks. Use the setup script to customise the topology and learning rate of the network. Experiment with exciting data sets, investigate the effects of hyperparameters and observe the data stream processing of the deep neural network. Watch how the network learns by processing the error stream during backpropagation.
- Date:
- Unscheduled
- Duration:
- 15 min
- Room:
- Conference:
- Snap!Con 2025
- Type:
- Talk
- Difficulty:
- Medium