A Plethora of Tools for Machine Learning When it comes to training computers to act without being explicitly programmed there exist an abundance of tools from the field of Machine Learning. Academics and industry professionals use these tools for building... read more
Intro to Machine Learning “We do not receive wisdom, we must discover it for ourselves, after a journey through the wilderness which no one else can make for us, which no one can spare us” –Marcel Proust Machine Learning is a subfield of... read more
Primary and Secondary Performance Metrics If you are building a classifier then you must measure it’s classification performance. If you are building a robot to pick up an object, you have to measure its ability to pick up objects. Any AI technology... read more
Introduction to Clustering Unsupervised learning is a machine learning method used to draw inferences from datasets consisting of input data without labeled responses [1]. In other words, it’s learning without the answer key. Knowledge discovery of ... read more
Reinforcement Learning Learning by interacting with our environment is perhaps the first form of learning that capable organisms discovered during the beginning of intelligence. Among the first examples were simple celled organisms that exercised the conn... read more
AHaH Computing, Thermodynamic Computing, Competitive Computing, Memristive Dot-product Engines, Dual Memristor Cross bars – are these all different names or variation of the same thing? All are gaining the attention of the academic and commercial re... read more
Introduction HelloTensorFlow aims to be a collection of notes, links, code snippets and mini-guides to teach you how to get Tensorflow up and running on MacOS (CPU only), Windows 10 (CPU and GPU) and Linux (work in progress) with zero experience in Tensor... read more
At Knowm, we are building a new and exciting type of computer processor to accelerate machine learning (ML) and artificial intelligence applications. The goal of Thermodynamic-RAM (kT-RAM) is to run general ML operations, traditionally deployed to CPUs an... read more
In this post, I demonstrate how to build Tensorflow 1.5 from source on MacOS 10.13 High Sierra. To verify that building indeed works, I show how to change some Tensorflow Python code, do an incremental build and observe the change in action via a simple t... read more
Prerequisites How To Setup Your Knowm Developer Environment What is Knowm? Thermodynamic Computing Introduction The Memristor Discovery platform is a low cost educational and research tool for exploring memristor electronics. Originally developed as a ris... read more