SLIDE 1
Cognition, computation, and crowdsourcing Jordan Suchow Human - - PowerPoint PPT Presentation
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 2
SLIDE 3
Experiment design == Algorithm design
Crowdsourcing
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
Developing efficient methods for training face-recognition abilities.
Example project
SLIDE 6
SLIDE 7
SLIDE 8
SLIDE 9
Can we do better?
SLIDE 10
SLIDE 11
What’s changed?
- 1. Hardware
- 2. Software/algorithms
- 3. Data
→ Deep neural networks trained on massive image databases using GPUs.
SLIDE 12
A “facespace”
SLIDE 13
SLIDE 14
Now we can ask…
What is the best algorithm for training face recognition abilities?
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
And crowd-based algorithms, too.
SLIDE 17
Align learned representations with psychological representations, such as: — Trustworthiness — Age — Gender dimorphism
SLIDE 18