Advertisement · 728 × 90

Posts by Mikail Khona

I just landed in Boston…giving my commencement speech at MIT tomorrow and I had the thought, “I wonder if I need a dress shirt for this” and, yall, I do.

10 months ago 4556 64 133 3
Post image

Attractors in ANNs mog attractors in brains

10 months ago 1 0 0 0
Post image

Our paper in @natcomms.nature.com, we show how cognitive maps in the hippocampal system could solve the general problem of representing and relating multiple alternative action plans. 
doi.org/10.1038/s414...

With @doellerlab.bsky.social, Patrick Haggard, @vigano.bsky.social, Daniel Reznik

11 months ago 94 30 7 1
Preview
Distinct synaptic plasticity rules operate across dendritic compartments in vivo during learning Synaptic plasticity underlies learning by modifying specific synaptic inputs to reshape neural activity and behavior. However, the rules governing which synapses will undergo different forms of plasti...

Our new paper is out in Science.

What is the synaptic plasticity rule in the brain, we asked. It turns out there are multiple, even within individual neurons.

Congrats Jake!

www.science.org/doi/10.1126/...

1 year ago 205 63 2 6
Preview
A prospective code for value in the serotonin system - Nature Merging ideas from reinforcement learning theory with recent insights into the filtering properties of the dorsal raphe nucleus, a unifying perspective is found explaining why serotonin neurons are ac...

Amazing @neuronaud.bsky.social
www.nature.com/articles/s41...
www.nature.com/articles/s41...

1 year ago 7 1 0 0
Preview
A neural mechanism for learning from delayed postingestive feedback - Nature Illness signals from the gut reactivate and strengthen flavour representations in the amygdala to support learning from delayed postingestive feedback.

How do we associate the flavors we experience during a meal 🍽️😋 with postingestive effects like food poisoning 🤢🤮 that arise much later?

Our answer in @nature.com this week: Illness signals from the gut reactivate and strengthen flavor representations in the amygdala.

📄: nature.com/articles/s41...

1 year ago 168 50 10 4

The easiest experiment would be to graft shampoo with the step size schedule of whatever optimizer you are currently using

1 year ago 0 0 0 0

Train your model with an optimizer that orthogonalizes gradients (like muon or shampoo) and maybe everything gets cleaned up even more

1 year ago 0 0 1 0
Post image

static-00.iconduck.com/assets.00/sa...

1 year ago 1 0 1 0
Advertisement