ttesmer

{-# LANGUAGE TypeSynonymInstances #-}
data Dual d = D Float d deriving Show
type Float' = Float

diff :: (Dual Float' -> Dual Float') -> Float -> Float'
diff f x = y'
  where D y y' = f (D x 1)

class VectorSpace v where
  zero  :: v

xdralex

Deep Learning

concepts

• forward and backward propagation
• vanishing gradient
• image convolution operation
• feature map, filter/kernel
• receptive field
• embedding
• translation invariance

niklasschmitz

import jax
from jax import core
from graphviz import Digraph
import itertools


styles = {
  'const': dict(style='filled', color='goldenrod1'),
  'invar': dict(color='mediumspringgreen', style='filled'),
  'outvar': dict(style='filled,dashed', fillcolor='indianred1', color='black'),

YingboMa

using ForwardDiff
goo((x, y, z),) = [x^2*z, x*y*z, abs(z)-y]
foo((x, y, z),) = [x^2*z, x*y*z, abs(z)-y]
function foo(u::Vector{ForwardDiff.Dual{T,V,P}}) where {T,V,P}
    # unpack: AoS -> SoA
    vs = ForwardDiff.value.(u)
    # you can play with the dimension here, sometimes it makes sense to transpose
    ps = mapreduce(ForwardDiff.partials, hcat, u)
    # get f(vs)
    val = foo(vs)

mdo

Ikea Bekant standing desk with Gerton table top