Keras - Python

 

Keras

If you like the Python-way of doing things, Keras is for you. It is a high-level library for neural networks, using TensorFlow or Theano as its backend. 

 

Keras - Artificial Intelligence Tools & Frameworks- edureka

 

The majority of practical problems are more like:

  • picking an architecture suitable for a problem,
  • for image recognition problems – using weights trained on ImageNet,
  • configuring a network to optimize the results (a long, iterative process).

    In all of these, Keras is a gem. Also, it offers an abstract structure that can be easily converted to other frameworks, if needed (for compatibility, performance, or anything).


    Comments

    Post a Comment

    Popular posts from this blog

    H20: Open Source AI Platform, Sparking Water

      H20: Open Source AI Platform H20 is an open-source deep-learning platform. It is an artificial intelligence tool that is business oriented and helps them to make a decision from data and enables the user to draw insights. There are two open-source versions of it: one is standard H2O and the other is paid version Sparkling Water. It can be used for predictive modeling, risk and fraud analysis, insurance analytics, advertising technology, healthcare, and customer intelligence.
    Read more

    ClimaCell - AI Accurate Weather

      ClimaCell  Headquarters:  Boston  Founders : Shimon Elkabetz (CEO), Rei Goffer, Itai Zlotnik  Funding:  $80 million  Valuation:  $217 million, via Pitchbook ClimaCell ’s cofounders all had what CEO Shimon Elkabetz describes as “life-threatening experiences due to poor weather forecasts” while serving in the Israeli military, inspiring them to try to find a way to make predictions more accurate. The company uses vast quantities of nontraditional data—like signals from cellphones, internet-of-things devices and street cameras—to issue hyperlocal “street-by-street, minute-by-minute” weather forecasts. More than 150 corporate customers, including JetBlue, the New England Patriots and ride-sharing service Via, are shelling out for its real-time predictions. 
    Read more

    Tamr - clean and organize dirty data

      Tamr Headquarters:  Cambridge, MA Founders : Andy Palmer (CEO), Ihab Ilyas, Mike Stonebraker  Funding:  $73.5 million Valuation:  $155 million, via Pitchbook Data management company Tamr was born out of an MIT research project to apply machine learning to clean and organize so-called dirty data that’s incomplete or inconsistent. Andy Palmer was running data engineering at pharmaceutical company Novartis when MIT’s system was brought in to organize a decade’s worth of biological assay information spread across more than 15,000 tables. The technology worked so well that he and two of the researchers decided to start a company around it. “The only way to curate thousands of tabular data sources that are constantly changing is using an artful combination of machine learning and human expertise,” says Palmer, who is now CEO. In practice, that means that Tamr’s system automatically identifies sources of data across a company that could be useful together and then tags in an employee to ins
    Read more