Creative Prediction with Neural Networks
A course in ML/AI for creative expression
Creative Prediction Practicalities
Charles Martin - The Australian National University
Python is powerful.
We can all be Python superheroes!
Python setup can be hard.
(Sorry)
Machine Learning Systems
GPUs; not just fun for games!
Colab to the Rescue?
On Premises: Workstations
- Workstations
- Pro: fun to play with
- Pro: good for small number of users
- Pro: one-time cost
- Con: not practical for many users
- Con: have to keep setting them up
- Con: I don’t like sharing?
Infrastructure-as-a-Service
- Virtual servers
- Set up server, access via Linux shell
- Amazon Web Services (AWS)
- Google Cloud Platform (GCP)
- DigitalOcean (DO)
- UH Cloud (UiO)
Platform-as-a-Service
- Google Cloud Kubenetes Engine
- Deploy “Containerised” application to servers.
- (Deploy DL to Kubernetes)
- Sigma2 (UiO)
get your tools together
Check out the setup page on creativeprediction.xyz.