I've been experimenting with a few neural network heavy algorithms. With the equity selection provided by an ETF Universe, I end up with say, 75 models needing to be trained and updated regularly. Over a several year backtest, the runtime basically crashes.
Any chance of GPU-acceleration support in the near-term?
To unlock posting to the community forums please complete at least 30% of Boot Camp.
You can continue your Boot Camp training progress from the terminal. We hope to see you in the community soon!