machine_learning   13598

« earlier    

tf.contrib.eager.defun  |  TensorFlow
Compiles a Python function into a callable TensorFlow graph.
TensorFlow  machine_learning 
7 hours ago by amy
AutoGraph converts Python into TensorFlow graphs – TensorFlow – Medium
We’d like to tell you about a new TensorFlow feature called “AutoGraph”. AutoGraph converts Python code, including control flow, print() and other Python-native features, into pure TensorFlow graph code.
TensorFlow  machine_learning  google 
yesterday by amy
[FoR&AI] Steps Toward Super Intelligence I, How We Got Here – Rodney Brooks
Some things just take a long time, and require lots of new technology, lots of time for ideas to ferment, and lots of Einstein and Weiss level contributors along the way.

I suspect that human level AI falls into this class. But that it is much more complex than detecting gravity waves, controlled fusion, or even chemistry, and that it will take hundreds of years.
AI  machine_learning  history 
yesterday by JohnDrake
scikit-learn: machine learning in Python — scikit-learn 0.19.2 documentation
scikit-learn

Machine Learning in Python

Simple and efficient tools for data mining and data analysis
python  programming  machine_learning 
yesterday by sharon_howard
Google AI Blog: Improving Connectomics by an Order of Magnitude
The field of connectomics aims to comprehensively map the structure of the neuronal networks that are found in the nervous system, in order to better understand how the brain works. This process requires imaging brain tissue in 3D at nanometer resolution (typically using electron microscopy), and then analyzing the resulting image data to trace the brain’s neurites and identify individual synaptic connections. Due to the high resolution of the imaging, even a cubic millimeter of brain tissue can generate over 1,000 terabytes of data! When combined with the fact that the structures in these images can be extraordinarily subtle and complex, the primary bottleneck in brain mapping has been automating the interpretation of these data, rather than acquisition of the data itself.

Today, in collaboration with colleagues at the Max Planck Institute of Neurobiology, we published “High-Precision Automated Reconstruction of Neurons with Flood-Filling Networks” in Nature Methods, which shows how a new type of recurrent neural network can improve the accuracy of automated interpretation of connectomics data by an order of magnitude over previous deep learning techniques. An open-access version of this work is also available from biorXiv (2017).
machine_learning  google  drosophila  neuroscience 
3 days ago by amy
google/ffn: Flood-Filling Networks for instance segmentation in 3d volumes.
Flood-Filling Networks for instance segmentation in 3d volumes.


Flood-Filling Networks (FFNs) are a class of neural networks designed for instance segmentation of complex and large shapes, particularly in volume EM datasets of brain tissue.

For more details, see the related publications:

https://arxiv.org/abs/1611.00421
https://doi.org/10.1101/200675
This is not an official Google product.
machine_learning  neuroscience  drosophila  google 
3 days ago by amy

« earlier    

related tags

!great  academic  adm  agribusiness  agriculture  ai  airline_industry  algorithms  archives  article  artificial  artificial_intelligence  bayesian  berit_anderson  bias  big_data  blockchain  book  books  brands  brett_horvath  bunge  calculus  cargill  cios  classification  clustering  cmu  collections  commodities  course  courses  criticism  d3  data_science  data_scientists  database  datascience  dataset  datasets  deep-learning  deep_learning  deepfakes  deeplearning  democratic-control  digital_archives  digital_art  digital_ethics  digitalization  dimension_reduction  distributed  drosophila  education  embeddings  ethics  ethics_of_algorithms  ex_nihilio  fake_facts  filter  food_crops  for_friends  free  games  gcp  generative  google  google_docs  gradient  grains  graph_limit  grim_meathook_future  hardware  health  healthcare  higher_ed  history  image  image_classification  images  informational_advantages  innovation  installation  intelligence  java  javascript  jetblue  k8s  kaggle  kalman  keras  kim  kubernetes  language  large_companies  learning  library  linear_algebra  louis_dreyfus  machine-learning  machine-minds  machinelearning  markov  math  matrix  metadata  ml  neural_network  neuroscience  nlp  observable  opensource  optimization  papers  partial_derivative  pca  politics  prediction  principais  programming  python  pytorch  reinforcement_learning  roger_mercer  scalar  sendhil.mullainathan  signal_processing  sklearn  slope  stacks  start_ups  statistics  system_design  tabular  teaching  tensorflow  tools  traders  tutorial  tutorials  university-ad-hoc  vector  visualization 

Copy this bookmark:



description:


tags: