Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
-
About
Hi!
-
Yes it's just doing compression. No it's not the diss you think it is.
In Ted Chiang’s New Yorker article, he likened language models to “a blurry JPEG”.
-
The New XOR Problem
In 1969, Marvin Minsky and Seymour Papert published Perceptrons: An Introduction to Computational Geometry.
-
Learning to Dequantise with Truncated Flows
A pet idea that I’ve been coming back to time and again is doing autoregressive language modelling with ``stochastic embeddings’’.
-
Vectorising The Inside Algorithm
This one goes by several names: CYK, Inside, Matrix chain ordering problem.
-
Smoothing With Backprop
If you’ve ever implemented forward-backward in an HMM (likely for a class assignment), you know this is an annoying exercise fraught with off-by-one errors or underflow issues.
-
Traversing Connectionist Trees
We’ve just put our paper “Recursive Top-Down Production for Sentence Generation with Latent Trees” up on ArXiv.
-
On “Better Exploiting Latent Variables in Text Modeling”
I’ve been working on latent variable language models for some time, and intend to make it the topic of my PhD.
-
Can Chinese Rooms Think?
There’s a tendency as a machine learning or CS researcher to get into a philosophical debate about whether machines will ever be able to think like humans.
-
Computing Log Normal for Isotropic Gaussians
Consider a matrix $\mathbf{X}$ with rows of datapoints $\mathbf{x_i}$ which are $(n, d)$.
-
Vectorisation and the logsumexp trick
Having played around and written up some simple machine learning algorithms the last couple of months, I've decided to write about some useful tricks of the trade that I've learnt.