Geoffrey Hinton and Nick Frosst debate language, intelligence, and the risks and rewards of AI at a headline Toronto Tech ...

The initial research papers date back to 2018, but for most, the notion of liquid networks (or liquid neural networks) is a new one. It was “Liquid Time-constant Networks,” published at the ...

We present a new neural network to approximate convex functions. This network has the particularity to approximate the function with cuts which is, for example, a necessary feature to approximate ...

In the desire to quantify the success of neural networks in deep learning and other applications, there is a great interest in understanding which functions are efficiently approximated by the outputs ...

While researchers have traditionally employed Gaussian processes (GP) for specifying prior and posterior distributions over functions, this approach becomes computationally expensive when scaled, is ...

In general, most of my colleagues and I use the term "network" or "net" to describe a neural network before it's been trained, and the term "model" to describe a neural network after it's been trained ...