Cognition, computation, and crowdsourcing Jordan Suchow Human - - PowerPoint PPT Presentation

cognition computation and crowdsourcing
SMART_READER_LITE
LIVE PREVIEW

Cognition, computation, and crowdsourcing Jordan Suchow Human - - PowerPoint PPT Presentation

Cognition, computation, and crowdsourcing Jordan Suchow Human ML/AI cognition Experiment design == Algorithm design Crowdsourcing Experiment design == Algorithm design 1 import numpy as np 2 import judicious 3 4 z2 =


slide-1
SLIDE 1

Cognition, computation, and crowdsourcing

Jordan Suchow

slide-2
SLIDE 2

ML/AI Human cognition

slide-3
SLIDE 3

Experiment design == Algorithm design

Crowdsourcing

slide-4
SLIDE 4

1 import numpy as np 2 import judicious 3 4 z2 = np.zeros(shape=(1, 16)) 5 6 for j in range(20): 7 8 noise = NOISE_LEVEL * np.random.normal(size=(N, 16)) 9 z2s = z2 + noise 10 11 ranks = judicious.rank_the( 12 catgory="Alan Turing", 13 images=z2s, 14 ) 15 w = [WEIGHTS[ranks.index(i)] for i in range(N)] 16 z2 = z2 + (ALPHA**j) * np.dot(noise.T, w)/(N*NOISE_LEVEL)

Experiment design == Algorithm design

slide-5
SLIDE 5

Developing efficient methods for training face-recognition abilities.

Example project

slide-6
SLIDE 6
slide-7
SLIDE 7
slide-8
SLIDE 8
slide-9
SLIDE 9

Can we do better?

slide-10
SLIDE 10
slide-11
SLIDE 11

What’s changed?

  • 1. Hardware
  • 2. Software/algorithms
  • 3. Data

→ Deep neural networks trained on massive image databases using GPUs.

slide-12
SLIDE 12

A “facespace”

slide-13
SLIDE 13
slide-14
SLIDE 14

Now we can ask…

What is the best algorithm for training face recognition abilities?

slide-15
SLIDE 15

Comparing many candidate algorithms:

— Hamiltonian Monte Carlo, other MCMC techniques — Stochastic gradient descent; search — Caricatures, morphs, and subtle distinctions — Active learning techniques, optimal pedagogy

slide-16
SLIDE 16

And crowd-based algorithms, too.

slide-17
SLIDE 17

Align learned representations with psychological representations, such as: — Trustworthiness — Age — Gender dimorphism

slide-18
SLIDE 18

Cognition, computation, and crowdsourcing

Jordan Suchow

ML/AI Human cognition