Deep Learning with Applications Using Python – Navin Kumar Manaswi

Deep Learning has come a really long way. From the birth of the idea to understand human mind and the concept of associationism — how we perceive things and how relationships of objects and views influence our thinking and doing, to the modelling of associationism which started in the 1870s when Alexander Bain introduced the first concert of Artificial Neural Networks by grouping the neurons.

Fast forward it to today 2018 and we see how Deep Learning has dramatically improved and is in all forms of life — from object detection, speech recognition, machine translation, autonomous vehicles, face detection and the use of face detection from mundane tasks such as unlocking your iPhoneX to doing more profound tasks such as crime detection and prevention.

  • Convolutional Neural Networks and Recurrent Neural Networks are shining brightly as they continue to help solve the world problems in literally all industry areas such as Automotive & Transportation,
  • Healthcare & Medicine, Retail to name a few. Great progress is being made in these areas and just metrics like these say enough about the palpability of the deep learning industry:
  • Number of Computer Science academic papers have soared to almost 10x since 1996
  • VCs are investing 6x more in AI startups since 2000
  • There are 14x more active AI startups since 2000
  • AI related jobs market is hiring 5x more since 2013 and Deep Learning is the most sought after skill in 2018
  • 84% of enterprises believe investing in AI will give them a great competi- tive edge.
  • The error rate of image classification has dropped from 28% in 2012 to 2.5% in 2017 and it is going down all the time!