Initialize the Weights
Discover why it is important to initialize weights and avoid dead neurons while building the neural network.
We'll cover the following
In
Fearful symmetry
Here is one rule to keep in mind: never initialize all the weights in a neural network with the same value. The reason for that recommendation is subtle, and comes from the matrix multiplications in the network. For example, let’s look at this matrix multiplication below:
Get hands-on with 1200+ tech skills courses.