A friend has just shown me this book "Calculus made easy", published in 1914, and I think it's got one of the best prologues I've ever seen. This is *exactly* what textbooks should be doing. And they should all be honest about how terrifying the topic names are too.
New preprint alert! We show that predictive coding is an emergent property of input-driven RNNs trained to be energy efficient. No hierarchical hard-wiring required. A thread: 1/
https://t.co/MCJFSPb49E
@alexbellos Thank you! New one for me: achieve a New Year's resolution before 1st Jan. I hadn't come across these before and am now hooked, have been doing them all evening.
I collected some free resources for learning computational neuroscience on my website. Please feel free to share with others and to send me suggestions.
https://t.co/Mki3brB1az
As a warm-up exercise to teach PCA I ask students to pretend they're a whale shark then ask them what angle they'd tilt their shark face if they were approaching a delicious krill swarm...
1/13) This semester's teaching on Bayesian stats and cognitive modeling is over! Thanks to COVID (ironically!), I recorded all my teaching sessions w/ @zoom_us, and they are available on #Youtube.
Wondered what have we covered to the cog-neuro audience? A thread.
1/7 A big problem with deepnet models of the brain is that they require training on huge supervised datasets. So even if they are approximations of neural responses in the "adult animal", the training process is a totally implausible model of learning in real visual development.
“First Order Motion Model for Image Animation” hooked up to a live camera:
https://t.co/9xXKMC06SP
Original NeurIPS2019 paper / code: https://t.co/yaOyMis5i6
For students and others interested in expanding their knowledge of AI during this period, we thought it might be helpful to ask our researchers what they consider to be the most impactful and insightful resources available to use #AtHomeWithAI (1/9)
To accommodate for this situation we are organizing one-day, virtual & free of charge Conference on AI inference in Practice in the first half of September 2020. The Conference will be accompanied by virtual workshops in topics of Deep Learning. More details will be posted soon!
How to run big (neuro)science conferences online — https://t.co/sIiqmr90Cl https://t.co/pzODe3yaOn what we learned. Let us make online conferences awesome.