RSSAmplifier

Blog

Engraved

Jonas Degrave's commentary on machine learning and the quest for artificial intelligence.

engraved.blogRSS feed ↗5 posts

Latest posts

Building A Virtual Machine inside ChatGPT

Unless you have been living under a rock, you have heard of this new ChatGPT assistant made by OpenAI. Did you know, that you can run a whole virtual machine inside of ChatGPT?

But why is diversification a free lunch?

In this post, I want to explain why diversification is a good idea. You might have heard that "diversification is the only free lunch in investing", but why is that the case?

Reviewing "The Fall and Rise of Democracy" By David Stasavage

I figured I needed to know more about the history of democracy, if I was ever going to fix this broken system of ours. That much was obvious after hearing David Stasavage talk on the MindScape podcast . Or at least gain an understanding as to why "the system"

How we can make machine learning algorithms tunable

In the previous blogpost, we established that machine learning algorithms are often hard to tune, and hopefully explained the mechanism for why gradient descent has difficulty with linear losses. In this blogpost, we will lay out some possible solutions.

Why machine learning algorithms are hard to tune and how to fix it

In machine learning, linear combinations of losses are all over the place. In fact, they are commonly used as the standard approach, despite that they are a perilous area full of dicey pitfalls.