Directions in ML: “Neural architecture search: Coming of age”

Neural Architecture Search (NAS) is a very promising but still young field. I will start this talk by discussing various works aiming to build a scientific community around NAS, including benchmarks, best practices, and open source frameworks. Then, I will discuss several exciting directions for the field: (1) a broad range of possible speedup techniques […]

Becoming Immortal for 10,000$? – Upload Your Mind THIS DECADE!

Becoming Immortal through Mind Uploading sounds like something that’ll only be possible around the 2100’s. But amazingly, a group of scientists at Nectome are working on giving us the ability to live forever inside of a computer simulation by the end of this decade for around 10000$. Ray Kurzweil, director of engineering at Google, has […]

Detecting Cancer with a RBF Network trained by a Genetic Algorithm

https://www.kickstarter.com/projects/jeffheaton/artificial-intelligence-for-humans-vol-2-nature-al This video shows a presentation for my winning entry in the Society of Actuaries 2013 Forecasting & Futurism genetic algorithm contest. For my entry I used a multi-threaded C# based genetic algorithm for training. This code is covered in my new book AIFH Vol 2: Nature Inspired Algorithms. See the above link. Source of […]

Artificial Intelligence for Humans, Volume 1: Fundamental Algorithms

For more information on the Kickstarter project, and how to pre-order, please visit http://www.jeffheaton.com/2013/06/kickstarter-project-now-13-funded/ This video provides a 10 minute 10,000 ft overview of AI. This is the same material that my upcoming book will cover. Source of this machine learning/AI Video

Teaching Computers about Language with the Skipgram Model | New NLP Course Announcement

The basic idea behind word embeddings and the skip gram model is something called distributional semantics: we can define words by the company they keep. Skip-gram is a technique that uses correlations between center words and their context words to define word vectors that capture the meaning of those words. The mathematics center around maximizing […]

DeepMind x UCL | Deep Learning Lectures | 7/12 | Deep Learning for Natural Language Processing

This lecture, by DeepMind Research Scientist Felix Hill, first discusses the motivation for modelling language with ANNs: language is highly contextual, typically non-compositional and relies on reconciling many competing sources of information. This section also covers Elman’s Finding Structure in Time and simple recurrent networks, the importance of context and transformers. In the second part, […]

800 Calorie Pancake of Peace | High Protein Pancake

I’ve cooked this breakfast food since 2013. It’s taken me a few years but I think I’ve nailed the recipe and cooking method. Simple is best. Ingredients: – 250g Egg Whites – 1 Cup Oatmeal – 1 Whole Banana – 30g Almond Butter (or substitute whatever nut butter you feel like) – 100g Mixed Berries […]

Probabilistic ML – Lecture 3 – Continuous Variables (updated 2021)

This is the third lecture in the Probabilistic ML class of Prof. Dr. Philipp Hennig in the Summer Term 2020 at the University of Tübingen, updated in 2021 Time-stamped slides available at https://uni-tuebingen.de/en/180804. Contents: * Random Variables and Borel Measures * Beta Distributions and a Conjugate Prior Example Some of the slides for this lecture […]

Probabilistic ML – Lecture 2 – Reasoning under Uncertainty

This is the second lecture in the Probabilistic ML class of Prof. Dr. Philipp Hennig in the Summer Term 2020 at the University of Tübingen. Time-stamped slides available at https://uni-tuebingen.de/en/180804. Contents: * Conditional Independence * Directed Graphical Models / Bayesian Networks Much of the content of this lecture is based on earlier material developed by […]

Probabilistic ML – Lecture 1 – Introduction

This is the first lecture in the Probabilistic ML class of Prof. Dr. Philipp Hennig in the Summer Term 2020 at the University of Tübingen. Time-stamped slides available at https://uni-tuebingen.de/en/180804. Contents: * Introduction to uncertain reasoning * Kolmogorov’s axioms and basic rules of probabilistic reasoning * Example uses of Bayes’ Theorem Slides 4 & 13 […]

Predicting Intensive Care Unit Mortality

AAAI 2015 paper: ” A Multivariate Timeseries Modeling Approach to Severity of Illness Assessment and Forecasting in ICU with Sparse, Heterogeneous Clinical Data” http://mghassem.mit.edu/wp-content/uploads/2013/02/ghassemi_AAAI2015_multivariate_timeseries_modeling.pdf YouTube Source for this AI Video

Who Invented A.I.? – The Pioneers of Our Future

— About ColdFusion — ColdFusion is an Australian based online media company independently run by Dagogo Altraide since 2009. Topics cover anything in science, technology, history and business in a calm and relaxed environment. If you enjoy my content, please consider subscribing! I’m also on Patreon: https://www.patreon.com/ColdFusion_TV Bitcoin address: 13SjyCXPB9o3iN4LitYQ2wYKeqYTShPub8 — ColdFusion Book written by […]