DeepLearning.AI

Better Than Backprop: Greedy InfoMax trains AI without end-to-end backpropagation.

End-to-end backpropagation and labeled data are the peanut butter and chocolate of deep learning. However, recent work suggests that neither is necessary to train effective neural networks to represent complex data.

Unsupervised Learning

Anima Anandkumar — The Power of Simulation: How simulation can be useful for supervised learning

We’ve had great success with supervised deep learning on labeled data. Now it’s time to explore other ways to learn: training on unlabeled data, lifelong learning, and especially letting models explore a simulated environment before transferring what they learn to the real world.

Unsupervised Learning

Anima Anandkumar — The Power of Simulation: How simulation can be useful for supervised learning

We’ve had great success with supervised deep learning on labeled data. Now it’s time to explore other ways to learn: training on unlabeled data, lifelong learning, and especially letting models explore a simulated environment before transferring what they learn to the real world.

Better Than Backprop: Greedy InfoMax trains AI without end-to-end backpropagation.

Anima Anandkumar — The Power of Simulation: How simulation can be useful for supervised learning

Anima Anandkumar — The Power of Simulation: How simulation can be useful for supervised learning

Subscribe to The Batch