The NWITS model

Prediction of the Next Word In The Sentence (NWITS) is the very definition and measure of a language model. It leaves out meaning, and for this reason it has become the subject of some derision, bordering on scorn, in spite of the remarkable capabilities of ChatGPT. If we modify this…

The Usual Suspects

Writing, Reading, Looking, Convolving Imagine you’re on a train. You pass the graffitied backs of warehouses, front-loaders parked in a snowy lot, a red-brick-and-white-wood apartment building, an electric company grid station, and then trees, a lake, and snow-dusted hills in the distance. If you turn your head, you can turn…

How Might a Human Machine Think?

How Might a Human Machine Think? In a Kaggle competition on distracted driving, the dataset consisted of images of drivers who either were or weren’t engaging in distracting activities. Rachel Thomas warns against “…overfitting to particularities of those specific people, and not just learning the states (texting, eating, etc). (emphasis added)”…

Generalization

Current AI really isn’t mimicking the brain, other than in name. “Neural networks” are indeed networks, but they really have very little to do with neurons. The general idea of an ‘activation function’ comes from neurons, but in AI it just means “if the aggregate addition of all these little…

On Recognition

The Mind of the Computer A Convolutional Neural Network learns to classify an image. What is the computer doing when it does this feat of ‘recognition’ ? Is it something we understand? Here is what we know. Digital images are submitted as inputs (grids of pixels, with RGB values, i.e., numbers). Then,…