Layer-wise learning for quantum neural networks (TF Dev Summit '20)

Inspired by classical training regimes, we show speedups in training times for quantum neural networks by training layers individually and in sweeps. We also show that this technique may be useful for overcoming the barren plateau problem for parameterized quantum circuits. Speaker: David Von Dollen - Volkswagen Group of America Watch all TensorFlow Dev Summit 2020 sessions → https://goo.gle/TFDS20 Subscribe to the TensorFlow YouTube channel → https://goo.gle/TensorFlow