ContentsThe library

The Mathematics of Gradient Descent

The Variance That Keeps a Deep Network Alive

Last timeA Step Size Per Coordinate

Initial weights have one job: keep the scale of the signal steady through every layer. Being a few percent off compounds into a factor of hundreds by layer fifty.

Everything in this course has assumed a starting point and then asked how to

move from it. This last lesson asks what the starting point has to be, and the

answer is not a matter of taste. A deep network initialised at the wrong scale

produces either no gradient at all or an infinite one, and neither can be

recovered from by tuning anything covered so far.

What one layer does to the scale

Take a layer with no activation function yet: y=Wxy = Wx, where xx has nn

components and the weights are drawn independently with mean zero.

Each output is a sum of nn terms, each a weight times an input. Independent

zero-mean terms add their variances, so:

FIG 1Variance through a linear layer
the fan-in, the number of inputs to the layer
the variance of a single weight, the quantity being chosen
the variance of an input component, which is the scale arriving from the previous layer
The width of the layer appears as a multiplier. A layer of a thousand inputs amplifies the variance a thousandfold unless the weights are shrunk deliberately to prevent it.

For the output to have the same scale as the input, the multiplier must be one:

The lesson stops here

9 more paragraphs to go

You have read the opening. The rest of the argument, the problems that check whether it landed, and the lines worth keeping at the end all come with a plan.

The first lesson of every course in the library reads the whole way through, free, so you can see exactly what the rest of them are.

See the planThe contents

This is the reading half

Starting the course gives you your own copy of it. Every idea on every page has problems standing under it, marked with a reason rather than a tick, and any sentence you do not believe can be opened and argued with. None of that can happen on a page nobody owns.

The contents

The rest of this course

  1. 01Why the Steepest Direction Is the Negative Gradient
  2. 02Why the Gradient Is Computed Backwardsopening only
  3. 03The Largest Step a Curvature Will Tolerateopening only
  4. 04One Ratio Decides How Long Training Takesopening only
  5. 05What Momentum Multiplies Your Step Size Byopening only
  6. 06The Gradient You Use Is Always the Wrong Oneopening only
  7. 07Dividing by the Size of Your Own Gradientsopening only
  8. 08The Variance That Keeps a Deep Network Aliveyou are here

Read alongside