Cédric Goemaere

For the last two years, I’ve been working on Predictive Coding (PC), a niche learning algorithm that serves as an alternative to backpropagation. From an ML perspective, PC is really bad: it scales poorly, it’s very slow, and it almost never beats backprop. But all of that doesn’t matter to... [Read More]

Deep Learning has been massively successful in recent years, in part because of the efficiency of its learning algorithm: backpropagation. However, the brain is also pretty good at learning(citation needed), and it’s definitely not doing backprop. One theory for how the brain learns, is Predictive Coding (PC), which has recently... [Read More]

The first year of my PhD eventually became a full deep dive into Hopfield networks. These neural networks, inspired by biological memory, promise a new direction for AI that is more biologically plausible than traditional Deep Learning — and significantly more energy-efficient. And yet, after that first year, I shifted... [Read More]

This post was inspired by Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One. It made me rethink how image classifiers work—it’s much more nuanced than you might suspect. [Read More]

Okay, maybe this is my first blog post. At least, on my new website! (I’m way too proud of having this thing up and running) [Read More]