papers   23629

« earlier    

[1712.01208] The Case for Learned Index Structures
"Indexes are models: a B-Tree-Index can be seen as a model to map a key to the position of a record within a sorted array, a Hash-Index as a model to map a key to a position of a record within an unsorted array, and a BitMap-Index as a model to indicate if a data record exists or not. In this exploratory research paper, we start from this premise and posit that all existing index structures can be replaced with other types of models, including deep-learning models, which we term learned indexes. The key idea is that a model can learn the sort order or structure of lookup keys and use this signal to effectively predict the position or existence of records. We theoretically analyze under which conditions learned indexes outperform traditional index structures and describe the main challenges in designing learned index structures. Our initial results show, that by using neural nets we are able to outperform cache-optimized B-Trees by up to 70% in speed while saving an order-of-magnitude in memory over several real-world data sets. More importantly though, we believe that the idea of replacing core components of a data management system through learned models has far reaching implications for future systems designs and that this work just provides a glimpse of what might be possible."
papers  database  indexing  machine-learning 
yesterday by arsyed
A Semantic Loss Function For Deep Learning With Symbolic Knowledge
"This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures how close the neural network is to satisfying the constraints on its output. An experimental evaluation shows that our semantic loss function effectively guides the learner to achieve (near-)state-of-the-art results on semi-supervised multi-class classification. Moreover, it significantly increases the ability of the neural network to predict structured objects, such as rankings and paths. These discrete concepts are tremendously difficult to learn, and benefit from a tight integration of deep learning and symbolic reasoning methods."
papers  neural-net  symbolic-reasoning 
2 days ago by arsyed
[1607.02533] Adversarial examples in the physical world
Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machine learning classifier to misclassify it. In many cases, these modifications can be so subtle that a human observer does not even notice the modification at all, yet the classifier still makes a mistake. Adversarial examples pose security concerns because they could be used to perform an attack on machine learning systems, even if the adversary has no access to the underlying model. Up to now, all previous work have assumed a threat model in which the adversary can feed data directly into the machine learning classifier. This is not always the case for systems operating in the physical world, for example those which are using signals from cameras and other sensors as an input. This paper shows that even in such physical world scenarios, machine learning systems are vulnerable to adversarial examples. We demonstrate this by feeding adversarial images obtained from cell-phone camera to an ImageNet Inception classifier and measuring the classification accuracy of the system. We find that a large fraction of adversarial examples are classified incorrectly even when perceived through the camera.
papers  adversarial-examples 
4 days ago by arsyed

« earlier    

related tags

2017  absolute-relative  academia  academic  acm  acmtariat  active-learning  adam-kalai  adversarial-examples  advice  ai  algorithms  amazon  annotation  applications  ar  arch  architecture  art  article  arvix  asr  baez  bandit  bayesian-optimization  bayesian  best-practices  bias  binary  biodet  bioinformatics  bitcoin  blog  blogged  book  causation  chrome  citations  classic  cnn  code  collaboration  collection  comment  community  compression  compsci  concept  conference  confounding  counterfactual  creativity  cs  curation  data  database  databases  dataset  deep-learning  deep_learning  descriptive  dimensionality  discovery  distribution  dl  download  drawing  ebook  econometrics  education  einstein  electromag  engine  engineering  ethics  experiment  experimental-design  explanation  exposition  extension  fatml  financial-econometrics  food  fp  free  funny  gan  gaussian-processes  generalization  generative  genetics  giants  google  graph  graphical-models  graphics  graphs  guide  gwas  hacker-news-comments  hackernews  hardware  history  hmc  humans  iclr-2018  indexes  indexing  induction  information_science  interdisciplinary  intricacy  intuition  ipad  ir  journals  latent-variables  launch_vehicles  learn  learning-theory  learning  liner-notes  links  list  livecoding  logic  ltr  machine-learning  machine_learning  machinelearning  manifolds  manuscripts  mapping  maths  mathtariat  mcmc  meshing  methodology  metrics  military  ml  mostly-modern  multi-armed  multi  neil-lawrence  neural-net  neural  nibble  nime2017  nips  nlp  noise-robustness  nonlinearity  notes  off-convex  oil-markets  ontology  org:bleg  org:edu  org:junk  org:mat  pac  paper  paradox  parsing  paywall  pdf  physics  plots  plugin  pop-structure  population-genetics  pre-ww2  preprint  priors-posteriors  probabilistic-programming  program  programming  project_ideas  publishing  pucp  pwl  questions  r  random-projections  raytracing  reading  reason  reasoning  recommendationsystems  redecentralize  reference  references  relativity  repository  representation-learning  research  residual  review  sample-complexity  sanjeev-arora  scholar  science  scientific  scoring  sculpture  search  semantic  serialization  simulation  software  space  speculation  speech  sql  stat-mech  state-of-art  statistics  stochastic-processes  suchi-saria  summary  survey  surveys  sus  symbolic-reasoning  synchrony  systems  tensegrity  tensorflow  text  the-trenches  theory  tidy  time-series-econometrics  time-series  tools  toread  torrents  usability  values  vc-dimension  videoai  virtualization  volo-avolo  vr  word-embedding  writing 

Copy this bookmark: