16 Building blocks for neural networks

8.16.0.4

16 Building blocks for neural networks🔗ℹ

The type block? consists of two fields, a block function and a block list.

procedure
(block b-fn block-ls) → block?
b-fn : (-> tensor? (-> (listof tensor?) tensor?))
block-ls : (listof shape?)

Creates a block from the block function b-fn and the block list block-ls.

procedure
(block-fn b) → (-> tensor? (-> (listof tensor?) tensor?))
b : block?

Returns the block function from the block b.

procedure
(block-ls b) → (listof shape?)
b : block?

Returns the block list from the block b.

procedure
(stack-blocks blocks) → block?
blocks : (listof block?)

Returns a new block where the block function is a composition of the block functions of each block in blocks in the order they appear in blocks, and the block list is created by appending the block lists of each block in blocks in the order they appear in blocks.

1	Overview
2	Entry points
3	List functions
4	Tensor functions
5	Extended Functions
6	Automatic Differentiation
7	Differentiable extended numerical functions
8	Non-differentiable extended numerical functions
9	Base-rank (non-extended) differentiable functions
10	Boolean comparison functions
11	Tensorized comparison functions
12	Hyperparameters
13	Gradient Descent Functions and Hyperparameters
14	Layer functions
15	Loss Functions
16	Building blocks for neural networks
17	He Initialization
18	Random number functions
19	Models and Accuracy
20	Logging
21	Utilities
22	Setting tensor implementations