sachaa + machinelearning   344

Open source software library for automated machine learning (AutoML)
keras  deeplearning  AI  machinelearning  library  api  opensource  development  python  automation  neuralnetwork 
january 2019 by sachaa
Open Images Dataset V4
Annotated images with bounding boxes, visual relationships, and image-level labels for 20,000 distinct concepts
data  dataset  training  google  opensource  AI  machinelearning  images  photography 
november 2018 by sachaa
Ontology Reasoning with Deep Neural Networks
The ability to conduct logical reasoning is a fundamental aspect of intelligent behavior, and thus an important problem along the way to human-level artificial intelligence. Traditionally, symbolic methods from the field of knowledge representation and reasoning have been used to equip agents with capabilities that resemble human reasoning qualities. More recently, however, there has been an increasing interest in applying alternative approaches based on machine learning rather than logic-based formalisms to tackle this kind of tasks. Here, we make use of state-of-the-art methods for training deep neural networks to devise a novel model that is closely coupled to symbolic reasoning methods, and thus able to learn how to effectively perform basic ontology reasoning. This term describes an important and at the same time very natural kind of problem settings where the rules for conducting reasoning are specified alongside with the actual information. Many problems in practice may be viewed as such reasoning tasks, which is why the presented approach is applicable to a plethora of important real-world problems. To demonstrate the effectiveness of the suggested method, we present the outcomes of several experiments that have been conducted on both toy datasets as well as real-world data, which show that our model learned to perform precise reasoning on a number of diverse inference tasks that require comprehensive deductive proficiencies. Furthermore, it turned out that the suggested model suffers much less from different obstacles that prohibit symbolic reasoning.
AI  research  ontology  machinelearning  deeplearning  paper  knowledgegraphs  logic 
august 2018 by sachaa
NLP-progress - Tracking Progress in Natural Language Processing
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
nlp  deeplearning  research  AI  machinelearning  ner  translation  speechrecognition  sentimentanalysis  textanalysis  classification  entityextraction 
august 2018 by sachaa
Microsoft Research Open Data
Collection of free datasets from Microsoft Research to advance state-of-the-art research in areas such as natural language processing, computer vision, and domain specific sciences
data  dataset  microsoft  research  machinelearning  AI  deeplearning  training  nlp  science  opensource 
july 2018 by sachaa
Attention Is All You Need
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.
nlp  rnn  cnn  research  paper  seq2seq  AI  machinecomprehension  machinelearning 
june 2018 by sachaa
Neural Discrete Representation Learning
Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector Quantised-Variational AutoEncoder (VQ-VAE), differs from VAEs in two key ways: the encoder network outputs discrete, rather than continuous, codes; and the prior is learnt rather than static. In order to learn a discrete latent representation, we incorporate ideas from vector quantisation (VQ). Using the VQ method allows the model to circumvent issues of "posterior collapse" -- where the latents are ignored when they are paired with a powerful autoregressive decoder -- typically observed in the VAE framework. Pairing these representations with an autoregressive prior, the model can generate high quality images, videos, and speech as well as doing high quality speaker conversion and unsupervised learning of phonemes, providing further evidence of the utility of the learnt representations.
deeplearning  research  paper  AI  embeddings  machinelearning 
june 2018 by sachaa
Boltzmann Encoded Adversarial Machines
Restricted Boltzmann Machines (RBMs) are a class of generative neural network that are typically trained to maximize a log-likelihood objective function. We argue that likelihood-based training strategies may fail because the objective does not sufficiently penalize models that place a high probability in regions where the training data distribution has low probability. To overcome this problem, we introduce Boltzmann Encoded Adversarial Machines (BEAMs). A BEAM is an RBM trained against an adversary that uses the hidden layer activations of the RBM to discriminate between the training data and the probability distribution generated by the model. We present experiments demonstrating that BEAMs outperform RBMs and GANs on multiple benchmarks.
research  paper  generative  AI  algorithms  machinelearning  neuralnetwork  deeplearning 
april 2018 by sachaa
A Mathematical Framework for Superintelligent Machines
We describe a class calculus that is expressive enough to describe and improve its own learning process. It can design and debug programs that satisfy given input/output constraints, based on its ontology of previously learned programs. It can improve its own model of the world by checking the actual results of the actions of its robotic activators. For instance, it could check the black box of a car crash to determine if it was probably caused by electric failure, a stuck electronic gate, dark ice, or some other condition that it must add to its ontology in order to meet its sub-goal of preventing such crashes in the future. Class algebra basically defines the eval/eval-1 Galois connection between the residuated Boolean algebras of 1. equivalence classes and super/sub classes of class algebra type expressions, and 2. a residual Boolean algebra of biclique relationships. It distinguishes which formulas are equivalent, entailed, or unrelated, based on a simplification algorithm that may be thought of as producing a unique pair of Karnaugh maps that describe the rough sets of maximal bicliques of relations. Such maps divide the n-dimensional space of up to 2n-1 conjunctions of up to n propositions into clopen (i.e. a closed set of regions and their boundaries) causal sets. This class algebra is generalized to type-2 fuzzy class algebra by using relative frequencies as probabilities. It is also generalized to a class calculus involving assignments that change the states of programs. 
INDEX TERMS 4-valued Boolean Logic, Artificial Intelligence, causal sets, class algebra, consciousness, intelligent design, IS-A hierarchy, mathematical logic, meta-theory, pointless topological space, residuated lattices, rough sets, type-2 fuzzy sets
AI  math  machinelearning  paper  research  algorithms  tweetit 
april 2018 by sachaa
« earlier      
per page:    204080120160

related tags

3D  abstracts  ai  airbnb  algorithms  amazon  analysis  annotation  api  apple  architecture  arduino  art  association  attention  audio  augmentedreality  automation  azure  bayesnetworks  BERT  bestpractices  bias  bigdata  bing  bioinformatics  biology  bitcoin  blogs  books  brain  business  Canada  capsulenetworks  car  career  chart  cheatsheet  chess  china  classification  cloudcomputing  clustering  cnn  cntk  cognitiveservices  comics  computervision  conference  constitution  contest  conversationalui  cooking  coreml  cortana  crf  crispr  crm  crowdsourcing  curation  data  database  datamining  dataset  debugging  decisiontrees  decor  deeplearning  demo  design  development  diagnosis  diffp  dimensionalityreduction  documentary  drawing  ebooks  economy  edgecomputing  education  ehr  electronics  embeddings  entityextraction  entrepreneurship  event  evolutionary  facebook  finance  fonts  fractals  framework  fun  future  gallery  gamedev  games  gan  generative  genetics  google  government  GPU  graphs  hacking  hardware  health  history  howto  ibm  icons  idea  ideas  illustration  imageprocessing  imagerecognition  images  influence  infographics  informationtheory  innovation  intelligenceaugmentation  intelligentaugmentation  interactiondesign  interview  iOS  IRL  java  javascript  jobs  jupyter  keras  km  knowledgegraphs  languages  law  leadership  learning  legal  library  linkeddata  logic  lsa  lstm  mac  machinecomprehension  machinelearning  machineteaching  marketing  math  mechanicalturk  medicine  metalearning  microsoft  midi  mindmap  mixedreality  models  mooc  motiondesign  motivation  music  ner  networking  neuralnetwork  neuroscience  nlp  ontology  opensource  paper  patternrecognition  patterns  performance  philosophy  photography  physics  presentation  prototyping  psychology  python  q&a  qlearning  questions  raspberrypi  realtime  reference  reinforcementlearning  religion  research  resources  rest  review  rnn  robots  scala  science  sdk  search  semanticweb  sentimentanalysis  seq2seq  signalprocessing  simulation  siri  sketching  socialnetworking  sociology  softwareengineering  spark  speechrecognition  sports  standards  statistics  stock  styleguide  summarization  support  synth  tagging  technology  tensorflow  textanalysis  textgeneration  texttospeech  todo  trading  training  transferlearning  translation  trends  troubleshooting  trust  tutorial  tweetit  twitter  typography  unitedstates  unity  university  ux  video  virtualization  virtualreality  visualization  web3.0  webapi  webdev  webgl  webtools  why  windows  windows10  word2vec  wordembedding  words  work 

Copy this bookmark: