The only algorithm I know for updation of weights of a neural network is based on gradients. The update equation can be roughly written as

$$w \leftarrow w - \nabla_{w}L$$

where $\nabla_{w}L$ is the gradient of loss function with respect to weights.

Are there any learning algorithms for updating weights in neural networks that does not use gradients?



A prominent class of "gradient-free" algorithms in ML world is known as Evolution Strategies (ES). Evolutionary Algorithms, although existed for a long time, only a few have shown to scale well.

Recently, the research group OpenAI managed to train Deep RL models with a specific variant of ES (with careful engineering). You can read this paper. This blog by David Ha provides a starting point if you want to learn about ES and its modern derivatives.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.