Главная
Study mode:
on
1
Intro
2
Intelligence: the greatest scientific adventure of all times
3
Peeking inside the brain
4
An image is worth a million words
5
Standing on the shoulders of giants: Mesoscopic connectivity of the primate visual system
6
Outline
7
Pattern completion is a hallmark of intelligence
8
Visual recognition of occluded objects
9
Visual inference from partial information
10
Strong robustness to limited visibility
11
Peeking inside the human brain
12
Neural mechanisms of pattern completion
13
Rumination through horizontal connections
14
Neurobiological recipe: add horizontal recurrent connections to deep convolutional networks
15
Eye movements are critical for scene understanding
16
We are legally blind outside the fovea
17
Four key properties of visual search
18
Active sampling during visual search
19
Invariant Visual Search Network (IVSN)
20
Neurally inspired model captures sampling behavior
Description:
Explore the fascinating intersection of neuroscience and artificial intelligence in this lecture by Gabriel Kreiman from Harvard University and Children's Hospital Boston. Delve into the complexities of brain codes and their potential applications in developing more advanced AI systems. Examine the intricacies of visual recognition, pattern completion, and neural mechanisms underlying these processes. Discover how the human brain processes partial information and completes patterns, and learn about the importance of eye movements in scene understanding. Gain insights into neurobiologically inspired models that capture sampling behavior and the potential for creating more robust and intelligent AI systems based on our understanding of brain function.

Deciphering Brain Codes to Build Smarter AI

MITCBMM
Add to list