Return to Question

I was reading Gary Marcus's a Critical Appraisal of Deep Learning. And one of his criticisms is that neural networks don't incorporate prior knowledge in tackling a problem. My question is, has there been any attempts at encoding prior knowledge in deep neural networks?

I was reading Gary Marcus's a Critical Appraisal of Deep Learning. One of his criticisms is that neural networks don't incorporate prior knowledge in tackling a problem. My question is: have there been any attempts at encoding prior knowledge in deep neural networks?