Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity

02/18/2016
by   Amit Daniely, et al.
0

We develop a general duality between neural networks and compositional kernels, striving towards a better understanding of deep learning. We show that initial representations generated by common random initializations are sufficiently rich to express all functions in the dual kernel space. Hence, though the training objective is hard to optimize in the worst case, the initial weights form a good starting point for optimization. Our dual view also reveals a pragmatic and aesthetic perspective of neural networks and underscores their expressive power.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset