Published:
📖 TL;DR: the next-token prediction of a transformer block taking some context and query as input is equivalent to the output of the same transformer with weights updated by the context and with only the query as input.
Published:
📖 TL;DR: Energy-based Transformers (EBTs) learn a scalar energy function parameterised by a transformer. Empirically, EBTs show promising scaling and reasoning properties on both language and vision tasks.
Published:
📖 TL;DR: We introduce \(\mu\)PC, a reparameterisation of predictive coding networks that enables stable training of 100+ layer ResNets with zero-shot hyperparameter transfer.
Published:
This is the third and last post of a short series on the infinite-width limits of deep neural networks (DNNs). In Part I, we showed that the output of a random network becomes Gaussian distributed in the infinite-width limit. Part II went beyond initialisation and showed that infinitely wide nets trained with GD are basically kernel methods.
Published:
This is the second post of a short series on the infinite-width limits of deep neural networks (DNNs). Previously, we reviewed the correspondence between neural networks and Gaussian Processes (NNGP), showing that, as the number neurons in the hidden layers grows to infinity, the output of a random network becomes Gaussian distributed.
Published:
This is the first post of a short series on the infinite-width limits of deep neural networks (DNNs). We start by reviewing the correspondence between neural networks and Gaussian Processes (GPs).
Published:
🤔 Confused about the recent KAN: Kolmogorov-Arnold Networks? I was too, so here’s a minimal explanation that makes it easy to see the difference between KANs and multi-layer perceptrons (MLPs).
Published:
📖 TL;DR: Predictive coding makes the loss landscape of feedforward neural networks more benign and robust to vanishing gradients.
Published:
I recently came across this paper Thermodynamic Natural Gradient Descent by Normal Computing. I found it very interesting, so below is my brief take on it.
Published:
📖 TL;DR: Predictive coding implicitly performs a 2nd-order weight update via 1st-order (gradient) updates on neurons that in some cases allow it to converge faster than backpropagation with standard stochastic gradient descent.
