nhaliday + interpretability   17

Peter Norvig, the meaning of polynomials, debugging as psychotherapy | Quomodocumque
He briefly showed a demo where, given values of a polynomial, a machine can put together a few lines of code that successfully computes the polynomial. But the code looks weird to a human eye. To compute some quadratic, it nests for-loops and adds things up in a funny way that ends up giving the right output. So has it really ”learned” the polynomial? I think in computer science, you typically feel you’ve learned a function if you can accurately predict its value on a given input. For an algebraist like me, a function determines but isn’t determined by the values it takes; to me, there’s something about that quadratic polynomial the machine has failed to grasp. I don’t think there’s a right or wrong answer here, just a cultural difference to be aware of. Relevant: Norvig’s description of “the two cultures” at the end of this long post on natural language processing (which is interesting all the way through!)
mathtariat  org:bleg  nibble  tech  ai  talks  summary  philosophy  lens  comparison  math  cs  tcs  polynomials  nlp  debugging  psychology  cog-psych  complex-systems  deep-learning  analogy  legibility  interpretability 
march 2017 by nhaliday

bundles : academeacm

related tags

acm  acmtariat  adversarial  ai  ai-control  analogy  analysis  apollonian-dionysian  atoms  average-case  best-practices  better-explained  bias-variance  big-picture  causation  classification  clever-rats  cog-psych  comparison  complex-systems  composition-decomposition  computation  computer-vision  concept  conceptual-vocab  conference  cs  data-science  dataviz  debugging  deep-learning  deep-materialism  deepgoog  defense  dennett  descriptive  dynamic  emergent  essay  events  exocortex  expert  expert-experience  exploratory  exposition  extrema  features  frontier  generalization  google  heterodox  homepage  huge-data-the-biggest  ideas  idk  info-dynamics  intelligence  interdisciplinary  interpretability  iteration-recursion  legibility  len:long  lens  let-me-see  longform  machine-learning  math  mathtariat  meta:prediction  meta:science  methodology  military  model-class  multi  neurons  news  nibble  nlp  open-closed  operational  optimization  org:bleg  org:edu  org:mag  org:mat  org:med  org:rec  org:sci  papers  pdf  perturbation  philosophy  pic  polynomials  popsci  preprint  psychology  ratty  reference  regularization  regularizer  research  research-program  rhetoric  risk  robust  scale  sequential  SIGGRAPH  slides  social-psych  social-science  software  speculation  speedometer  strategy  structure  study  summary  symmetry  talks  tcs  tech  technology  techtariat  the-self  theory-of-mind  thinking  tools  truth  turing  ui  values  visual-understanding  visualization  wiki  workshop  worrydream  🖥 

Copy this bookmark:



description:


tags: