artificial-intelligence   1214

« earlier    

[1703.07929] Diversification-Based Learning in Computing and Optimization
Diversification-Based Learning (DBL) derives from a collection of principles and methods introduced in the field of metaheuristics that have broad applications in computing and optimization. We show that the DBL framework goes significantly beyond that of the more recent Opposition-based learning (OBL) framework introduced in Tizhoosh (2005), which has become the focus of numerous research initiatives in machine learning and metaheuristic optimization. We unify and extend earlier proposals in metaheuristic search (Glover, 1997, Glover and Laguna, 1997) to give a collection of approaches that are more flexible and comprehensive than OBL for creating intensification and diversification strategies in metaheuristic search. We also describe potential applications of DBL to various subfields of machine learning and optimization.
metaheuristics  coevolution  to-write-about  system-of-professions  artificial-intelligence 
3 days ago by Vaguery
Demo - Lyrebird

Lyrebird will offer an API to copy the voice of anyone. It will need as little as one minute of audio recording of a speaker to compute a unique key defining her/his voice. This key will then allow to generate anything from its corresponding voice. The API will be robust enough to learn from noisy recordings. The following sample illustrates this feature, the samples are not cherry-picked.
Please note that those are artificial voices and they do not convey the opinions of Donald Trump, Barack Obama and Hillary Clinton.
voice  artificial-intelligence 
5 days ago by javierruiz
Magic AI: these are the optical illusions that trick, fool, and flummox computers
"The problem with the decision boundary approach to classification, says Clune, is that it’s too absolute, too arbitrary. 'All you’re doing with these networks is training them to draw lines between clusters of data rather than deeply modeling what it is to be leopard or a lion.' Systems like these can be manipulated in all sorts of ways by a determined adversary. To fool the lion-leopard analyzer, you could take an image of a lion and push its features to grotesque extremes, but still have it register as a normal lion: give it claws like digging equipment, paws the size of school buses, and a mane that burns like the Sun. To a human it’s unrecognizable, but to an AI checking its decision boundary, it’s just an extremely liony lion."
a:James-Vincent  p:The-Verge★  d:2017.04.12  w:2000  artificial-intelligence  security  from twitter
9 days ago by bankbryan
Business Insider - AI and trust
Tom Gruber, who leads the Siri team at Apple, says explainability is a key consideration for his team as it tries to make Siri a smarter and more capable virtual assistant. Gruber wouldn’t discuss specific plans for Siri’s future, but it’s easy to imagine that if you receive a restaurant recommendation from Siri, you’ll want to know what the reasoning was. Ruslan Salakhutdinov, director of AI research at Apple and an associate professor at Carnegie Mellon University, sees explainability as the core of the evolving relationship between humans and intelligent machines. “It’s going to introduce trust,” he says.
artificial-intelligence  technology 
10 days ago by xianoforange
[1703.06207v1] Cooperating with Machines
"Since Alan Turing envisioned Artificial Intelligence (AI) [1], a major driving force behind technical progress has been competition with human cognition. Historical milestones have been frequently associated with computers matching or outperforming humans in difficult cognitive tasks (e.g. face recognition [2], personality classification [3], driving cars [4], or playing video games [5]), or defeating humans in strategic zero-sum encounters (e.g. Chess [6], Checkers [7], Jeopardy! [8], Poker [9], or Go [10]). In contrast, less attention has been given to developing autonomous machines that establish mutually cooperative relationships with people who may not share the machine's preferences. A main challenge has been that human cooperation does not require sheer computational power, but rather relies on intuition [11], cultural norms [12], emotions and signals [13, 14, 15, 16], and pre-evolved dispositions toward cooperation [17], common-sense mechanisms that are difficult to encode in machines for arbitrary contexts. Here, we combine a state-of-the-art machine-learning algorithm with novel mechanisms for generating and acting on signals to produce a new learning algorithm that cooperates with people and other machines at levels that rival human cooperation in a variety of two-player repeated stochastic games. This is the first general-purpose algorithm that is capable, given a description of a previously unseen game environment, of learning to cooperate with people within short timescales in scenarios previously unanticipated by algorithm designers. This is achieved without complex opponent modeling or higher-order theories of mind, thus showing that flexible, fast, and general human-machine cooperation is computationally achievable using a non-trivial, but ultimately simple, set of algorithmic mechanisms. "
paper  cooperation  machine  artificial-intelligence  machine-learning 
13 days ago by tsuomela

« earlier    

related tags

##pvlpo-project  a:james-vincent  academic_lab  aggregation  ai  alan-jacobs  algorithm  algorithms  allan-newell  analytics  api  apollowebstudio  apple  approximation  archaeology  archives  art  artificial-neural-network  artificial  auditing  augmented-human-intelligence  automation  basic-income  bias  book  books  buddhism  budismo  catalog  citations  coevolution  cognitive  collective-intelligence  complexity  compliance  computer-science  consider:looking-to-see  consider:performance-space-analysis  consider:representation  content-samurai  cooperation  course  cpp  creative-coding  cryptography  curated  cyberculture  cyborgs  d:2017.04.12  data  dataset  decision-making  deep-learning  deep_learning  deeplearning  delong  design  dev-tools  development  discovery  distributed-processing  douglas-hofstadter  economics  email  encryption  evolution  experiments  facebook  forecasting  frameworks  future  futurism  game-dev  game-development  games  gaming  germany  github  google  graphics/resources  graphics/tools  gta-v  gta  guide  hacker-news-comments  health  herbert-simon  history  hn  homomorphic  homomorphic_encryption  humor  image-analysis  image-processing  images  intelligence  interview  ios  javascript  jobs  jonh-mccarthy  journalism  laar  labor  language  learning  libraries  machine-learning  machine  machinelearning  math  mechatronics  metaheuristics  metaphor  microsoft  minimax  mit  ml  mobile  natural-language-processing  neural-network  neural-networks  neuralnetworks  news  noosphere  nudge-targets  nytimes  ocw  open-ai  openai  p:the-verge★  paper  person-of-interest  pessimism  philosophers'-conference  philosophy-of-engineering  philosophy  photography  plane-geometry  playground  polisci:ideology  programming  psychology  public-knowledge  public  python  rather-interesting  records_management  reference  reinforcement-learning  representation  resources  robotics  robots  science-fiction  science  search-engine  security  self-driving  sharing  singularity  sociology  speech-recognition  stanford  statistics  summarise  summarize  summarizer  summary  system-of-professions  teaching-computer  technology  television  tensorflow  text  to-read  to-write-about  traditional-methods  tutorial  type:collection  video  voice  w:2000  web-dev-tools  web-dev  web-development  web_programming  webapp  webdevappmodule  webservice  weekly-guide  wired  work  wtf  zeichnen 

Copy this bookmark: