ComputerVision Talks: Asynchronous Perception Machine
Explaining how APMs were a step towards getting GLOM to work well.

Making GLOM Work
GLOM was a theoretical idea in 2021. Here, we discuss what were some key ideas towards getting it to work.

Putting an End to End to End Gradient Descent
A learning algorithm (by Sindy Loewe) which trains each layer of a neural net in ‘isolation’ greedily. Optimization is based on a local-constraint (called Greedy-InfoMax)

Forward Forward Algorithm: Part 1/2
Neural net is optimized by piping input data sequentially with two forward passes

Forward Forward Algorithm: Part 2/2
Discussions on philosophical ideas in Forward Forward paper, for eg, getting rid of gradient descent, mortal computation.

Backpropagation And Brain
How can backpropagation be made more biologically plausible?

Target Propagation
An approach to avoid computing derivatives of neurons, and eliminate reliance on chain rule. Pipe error signal back into the network.

Autoencoding Assumption
Autoencoder can be used to compute top-down neural activities on the fly.

Weight Transport Problem
Backpropagation requires computing transpose of weight matrix. Brain doesn't do transpose.

Memory Explosion Issue in Attention
Attention is quadratic in time/memory. Linear Attention/Mamba etc can do linear time.