Demystifying Machine Learning Part 2: Supervised, Unsupervised, and Reinforcement Learning

Machine learning use cases #AI:

1. Supervised
2. Unsupervised
3. Reinforcement #DF16

  • You start by showing a block and then placing the block in the block box; similarly you pick up a soft toy and then place it in the toy box.
  • Unsupervised learning is a somewhat harder form of machine learning.
  • Very quickly after a few iterations the child learns which toys need to go into which box – this is called Reinforcement Learning .
  • Just as the three year old learns the difference between a ‘block’ and a ‘soft toy’, the supervised machine learning system learns which email is ‘spam’ and which is ‘not spam’.
  • For example, a supervised machine learning system that can learn which emails are ‘spam’ and which are ‘not spam’ will have its input data tagged with this classification to help the machine learning system learn the characteristics or parameters of the ‘spam’ email and distinguish it from those of ‘not spam’ emails.

Where business and experience meet emerging technology.
Continue reading “Demystifying Machine Learning Part 2: Supervised, Unsupervised, and Reinforcement Learning”

Demystifying Machine Learning Part 2: Supervised, Unsupervised, and Reinforcement Learning

Machine learning use cases #AI:

1. Supervised
2. Unsupervised
3. Reinforcement

  • You start by showing a block and then placing the block in the block box; similarly you pick up a soft toy and then place it in the toy box.
  • Unsupervised learning is a somewhat harder form of machine learning.
  • Very quickly after a few iterations the child learns which toys need to go into which box – this is called Reinforcement Learning .
  • Just as the three year old learns the difference between a ‘block’ and a ‘soft toy’, the supervised machine learning system learns which email is ‘spam’ and which is ‘not spam’.
  • For example, a supervised machine learning system that can learn which emails are ‘spam’ and which are ‘not spam’ will have its input data tagged with this classification to help the machine learning system learn the characteristics or parameters of the ‘spam’ email and distinguish it from those of ‘not spam’ emails.

Where business and experience meet emerging technology.
Continue reading “Demystifying Machine Learning Part 2: Supervised, Unsupervised, and Reinforcement Learning”

Demystifying Machine Learning Part 2: Supervised, Unsupervised, and Reinforcement Learning

Machine learning use cases #AI

  • You start by showing a block and then placing the block in the block box; similarly you pick up a soft toy and then place it in the toy box.
  • Unsupervised learning is a somewhat harder form of machine learning.
  • For example, a supervised machine learning system that can learn which emails are â spamâ and which are â not spamâ will have its input data tagged with this classification to help the machine learning system learn the characteristics or parameters of the â spamâ email and distinguish it from those of â not spamâ emails.
  • Control theoretic techniques and Markov decision processes are types of reinforcement learning.
  • Now instead of telling the child which toy to put in which box, you reward the child with a â big hugâ when it makes the right choice and make a â sad faceâ when it makes the wrong action (e.g., block in a soft toy box or soft toy in the block box).

In this blog we explore different types of machine learning.
Continue reading “Demystifying Machine Learning Part 2: Supervised, Unsupervised, and Reinforcement Learning”

Welcome to TensorLayer — TensorLayer 1.1 documentation

TensorLayer: #DeepLearning and Reinforcement learning library for #TensorFlow.

  • Built with Sphinx using a theme provided by Read the Docs .
  • Free document hosting provided by Read the Docs .
  • If you got problem to read the docs online, you could download the repository on GitHub , then go to /docs/_build/html/index.html to read the docs offline.
  • Versions latest Downloads pdf htmlzip epub On Read the Docs Project Home Builds
  • TensorLayer is a deep learning and reinforcement learning library for researchers and practitioners.

TensorLayer is a deep learning and reinforcement learning library for researchers and practitioners. It is an extension library for Google TensorFlow. It providers high-level APIs and pre-built training blocks that can largely simplify the development of complex learning models. TensorLayer is easy to be extended and customized for your needs. In addition, we provide a rich set of examples and tutorials to help you to build up your own deep learning and reinforcement learning algorithms.
Continue reading “Welcome to TensorLayer — TensorLayer 1.1 documentation”