explanation   5241

« earlier    

Explicating Top-Down Causation Using Networks and Dynamics | Philosophy of Science: Vol 84, No 2
In many fields in the life sciences investigators refer to downward or top-down causal effects. Craver and I defended the view that such cases should be understood in terms of a constitution relation between levels in a mechanism and intralevel causal relations (occurring at any level). We did not, however, specify when entities constitute a higher-level mechanism. In this article I appeal to graph-theoretic representations of networks, now widely employed in systems biology and neuroscience, and associate mechanisms with modules that exhibit high clustering. As a result of interconnections within clusters, mechanisms often exhibit complex dynamic behaviors that constrain how individual components respond to external inputs, a central feature of top-down causation.
philosophy_of_science  networks  social_networks  dynamics  explanation  causality 
5 hours ago by rvenkat
Explainable Artificial Intelligence
New machine-learning systems will have the ability to explain their rationale, characterize their strengths and weaknesses, and convey an understanding of how they will behave in the future. The strategy for achieving that goal is to develop new or modified machine-learning techniques that will produce more explainable models. These models will be combined with state-of-the-art human-computer interface techniques capable of translating models into understandable and useful explanation dialogues for the end user (Figure 2). Our strategy is to pursue a variety of techniques in order to generate a portfolio of methods that will provide future developers with a range of design options covering the performance-versus-explainability trade space.
A-I  explanation  Futurism  engineering  machine_learning 
3 days ago by suitable
En hypotetisk riksdag
Höginkomsttagare röstar blått, och LO-medlemmar rött. Eller? Med data från SCB* kan du själv testa hur riksdagen skulle kunna se ut om en viss grupp fick bestämma.
explanation 
19 days ago by johanl
What is a likelihood anyway?
In order to fit Bayesian models we need to construct a function that tells us when certain values of model unknowns are good or bad. For example, in image Figure 2, we plot a histogram of values of some random variable X. We want to fit a density function to this histogram so as to be able to make probabilistic statements about the likely distribution of yet-unseen observations. To gauge which proposed density is a good one, we would like a function that gives a higher value for the proposed model unknowns that lead to the distribution in the bottom panel and lower values for the proposed model unknowns that lead to distribution in the top panel.
stats  math  explanation  jupyter  bayes  read-later 
21 days ago by kmt

« earlier    

related tags

***  2  2017  2018-08-15  240a  a-i  a  about  absolute  adoption  ai  algorithm  algorithms  amazing  american  ami  analysis  android  animation  anonymity  ansible  api  apple  argument  arms  article  ascii  assets  assign  assignin  at  attention  austerity  authentication  auto  aws  back  backend  bayes  beautiful  beautifultable  bizarre  black  blockchain  blog  books:noted  brexit  c++  caching  camera  canon6d  cares  case  categories  causal_inference  causality  caveat  charukesi  chmod  circuit  classification  cloud  codecartoons  collections  color  colorblind  colours  comic  command  commandline  communication  compare  comparison  complexity  component  concepts  condensate  condensation  conferences  config  configuration  consistency  control  cool  cost  crdt  critique  crypto  cryptography  css  csv  culture  dagger  darnold  dat  data  datastructure  datatypes  dba.stackexchange  description  design  desired  detailed  detection  development  diagram  difference  differences  directory  discount  distributedcomputing  distribution  dns  dsp  dynamics  ebs  ec2  ecommerce  email  emergence  encoding  end  engineering  error  eventual  example  excel  exhaust  experiment  explain  exploration  expressions  fantastic  features  fees  filter  fix  flag  food  for  format  forms  forum  framework  front  frontend  full  functions  futurism  g  gdpr  git  gives  global  good  google  gotcha  graphql  group  guide  gutenberg  hair  has  haskell  have_read  heater  hiring  historiography  history  hosts  how  howto  hsls  http  https  hyphen  i  id  illustrated  image  implementation  import  in  information  inline  int  interactive  interactivediagram  interesting  internet  interpretability  interventions  interview  introduction  ishihara  ja  javascript  jupyter  kanye  knowledge  kubernetes  layouts  learning  library  linux  liquid  list  lodash  logic  lucid  machine_learning  machinelearning  macos  macosx  magic_lantern  markov  materiality  math  matrices  max  medium  merge  method  migration  min  mobile  model  module  montecarlo  move  multiple  mysql  mysql5.7  narrative  navien  nd_filter  nerf  networking  networks  neuroscience  normal  npe  nrt  oauth  oauth2  of  ordt  overview  packages  parent  partial  password  paths  pdf  people  perception  perspective  philosophy_of_science  photography  php-fpm  physics  pipe  podcast  politics  pool  post  poverty  price  priceless  prime  print  privacy  process-tracing  product  programming  proof  proviso  public-radio  python  python2.7  question  questions  race  rapidstrike  rationalism  react  reactjs  read-later  realogy  rebase  recruiting  recruitment  redcap  reference  regular  relational  relative  resistance  resources  rest  restful  roles  root  rule  sam  sass  scaling  science  scientism  screencast  script  search  seo  serversforhackers  set  setgid  setup  sexism  shaders  shell  shopify  simple  sketch  slope  social_networks  sociology  software  sothebys  speed  spreadsheet  stackexchange  stackoverflow  start  statements  statistics  stats  store  storing  sts  style  stylesheet  subcategories  support  sync  syntax  table  tabular  tags  tankless  template  templates  temporal  test  the  theme  thermostat  three  time-lapse  time  tips  to:nb  tolearn  toread  totry  tounderstand  trading  troubleshoot  trump  tutorial  tweet  twitter  type-theory  types  ui  underscore  unicode  unity  university  unix.stackexchange  update  us  utf8  ux  vectors  vendors  vent  video  viral  virtual  visual  visualization  volume  vox  vue  vuejs  water  wavelets  web  website  websites  why  windows  wiring  wordpress  work  xai  yaml  yarkoni.tal  zero-knowledge  zero 

Copy this bookmark:



description:


tags: