Excellent guide for Installing Keras, Theano on Windows 10

For those of you who prefer trying out Deep Learning on Windows 10 with your GPU-enabled PC/laptop, here’s an excellent post by Fabien Tence on installing the frameworks you need.

http://ankivil.com/installing-keras-theano-and-dependencies-on-windows-10/

Keras is a high-level neural networks library, written in Python and capable of running on top of either TensorFlow or Theano.

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently.

Have fun!

 

Life Cycle of training the Artificial Neural Network

In the earlier post “Genesis of Deep Learning. Neuron & Artificial Neural Network (ANN)“, we discussed about the neuron and how a bunch of neurons forms an ANN. In this post, let’s have a quick appreciation and intuition on the typical life cycle of training an ANN.

Fig 1. Life cycle of training an ANN

What-If Thought. Correlation of Trust and Human-like deep learning on sparse data.

Difference between Human Learning and AI Learning? One of the key differences often highlighted is that a human can learn and generalise new concepts from one or few examples whereas the most powerful deep learning AI neural nets often need to learn from thousands to tens of thousands (or even millions) of examples. This implies current mainstream deep learning methods are not exactly human-like in learning. Is it possible then to model human learning?

Designed by Freepik

Genesis of Deep Learning. Neuron & Artificial Neural Network (ANN)

In the beginning, there was (and still is) the neuron. A neuron is the basic building block of artificial neural networks, which forms the basic architecture for Deep Learning today.

Fig 1. Illustration of a neuron and its inputs

First post and some thoughts

So I’ve embarked on a new journey that is exciting and challenging. Taking on a new role within the hot technology space of AI and more specifically, Deep Learning. It is my personal hope that through this blog, I will be able to share my learnings and news bytes and connect with people who are also keen in this area. So stay tuned!