Sign in / Sign up
The Holographic Principle: Why Deep Learning Works

The Holographic Principle: Why Deep Learning Works

What I want to talk to you about today is the Holographic Principle and how it provides an explanation to Deep Learning. The Holographic…
Go to the profile of Carlos E. Perez
Carlos E. Perez
The Two Phases of Gradient Descent in Deep Learning

The Two Phases of Gradient Descent in Deep Learning

Thanks to great experimental work by several research groups studying the behavior of Stochastic Gradient Descent (SGD), we are…
Go to the profile of Carlos E. Perez
Carlos E. Perez
The Black Magic and Alchemy of Deep Learning

The Black Magic and Alchemy of Deep Learning

The practice of Deep Learning is vastly outpacing theory. This is despite the incredible number of Deep Learning papers that are published…
Go to the profile of Carlos E. Perez
Carlos E. Perez
Latest
Chatbots: Theory and Practice

Chatbots: Theory and Practice

There’s a lot of fluff surrounding chatbots, so I wrote this post to lay out the basics. I first review the theory of conversation to give…
Go to the profile of Jonathan Mugan
Jonathan Mugan
Building a 50 Teraflops AMD Vega Deep Learning Box for Under $3K

Building a 50 Teraflops AMD Vega Deep Learning Box for Under $3K

In 2002, the fastest supercomputer in the world (i.e. “NEC Earth Simulator) was capable of 35.86 teraflops.
Go to the profile of Carlos E. Perez
Carlos E. Perez
Monetizing Artificial Intelligence

Monetizing Artificial Intelligence

Turn your AI software projects into an ATM machine. Freelance workers enable the automation of their work — ironically.
Go to the profile of gk_
gk_
Deep adversarial learning is finally ready 🚀 and will radically change the game

Deep adversarial learning is finally ready 🚀 and will radically change the game

Adversarial learning is one of the most hyped areas in deep learning. If you browse arxiv-sanity, you’ll notice much of the most popular…
Go to the profile of Michael Dietz
Michael Dietz
The Strange Loop in Deep Learning

The Strange Loop in Deep Learning

Douglas Hofstadter in his book “I am a Strange Loop” coined this idea:
Go to the profile of Carlos E. Perez
Carlos E. Perez
Barriers of Entry for Deep Learning Ventures

Barriers of Entry for Deep Learning Ventures

Venture capitalists (VCs) have a new term “Systematic Intelligence” that is worth paying attention to. Gil Dibner wrote an excellent…
Go to the profile of Carlos E. Perez
Carlos E. Perez
Businesses Need Artificial “Specialist” Intelligence, Not the Other Kind

Businesses Need Artificial “Specialist” Intelligence, Not the Other Kind

Here is the stark reality about businesses, we need specialists to do almost all our jobs. What this means in terms of the development of…
Go to the profile of Carlos E. Perez
Carlos E. Perez
Navigating the Unsupervised Learning Landscape

Navigating the Unsupervised Learning Landscape

Unsupervised learning is the Holy Grail of Deep Learning. The goal of unsupervised learning is to create general systems that can be…
Go to the profile of Eugenio Culurciello
Eugenio Culurciello
How to Re-Invent the Cognitive Stack of Intelligence

How to Re-Invent the Cognitive Stack of Intelligence

Kevin Kelly (founding editor of Wired magazine) just wrote a near disaster of an article “The AI Cargo Cult: The Myth of Superhuman AI.…
Go to the profile of Carlos E. Perez
Carlos E. Perez
Seven Deadly Sins and Artificial Intelligence Safety

Seven Deadly Sins and Artificial Intelligence Safety

It occurred to me one day that the seven deadly sins, that is:
Go to the profile of Carlos E. Perez
Carlos E. Perez
Writing Travel Blogs with Deep Learning

Writing Travel Blogs with Deep Learning

We all got excited with the recent developments of deep neural networks. Among the different applications of deep learning, Natural…
Go to the profile of Simone Romano
Simone Romano
The AI Economy is Reserved for the Highly Skilled

The AI Economy is Reserved for the Highly Skilled

Thomas Frey has a thought provoking article “78 Skills that are Difficult to Automate”. Frey breaks down the categories of jobs that he…
Go to the profile of Carlos E. Perez
Carlos E. Perez
Deep Learning Unknowable Knowns

Deep Learning Unknowable Knowns

One good way to frame the question of the limits of Deep Learning is in the context of the Principle of Computational Equivalence by…
Go to the profile of Carlos E. Perez
Carlos E. Perez
About Intuition MachineLatest StoriesArchiveAbout MediumTermsPrivacy