dl for neuro
Contents
1.12. dl for neuro#
1.12.1. Ideas for neuroscience using deep learning#
list of comparisons: https://docs.google.com/document/d/1qil2ylAnw6XrHPymYjKKYNDJn2qZQYA_Qg2_ijl-MaQ/edit
Modern deep learning evokes many parallels with the human brain. Here, we explore how these two concepts are related and how deep learning can help understand neural systems using big data.
1.12.2. Brief history#
The history of deep learning is intimately linked with neuroscience, with the modern idea of convolutional neural networks dates back to the necognitron
1.12.2.1. pro big-data#
Artificial neural networks can compute in several different ways. There is some evidence in the visual system that neurons in higher layers of visual areas can, to some extent, be predicted linearly by higher layers of deep networks
when comparing energy-efficiency, must normalize network performance by energy / number of computations / parameters
1.12.2.2. anti big-data#
could neuroscientist understand microprocessor
no canonical microcircuit
1.12.3. Data types#
EEG |
ECoG |
Local Field potential (LFP) -> microelectrode array |
single-unit |
calcium imaging |
fMRI |
|
---|---|---|---|---|---|---|
scale |
high |
high |
low |
tiny |
low |
high |
spatial res |
very low |
low |
mid-low |
x |
low |
mid-low |
temporal res |
mid-high |
high |
high |
super high |
high |
very low |
invasiveness |
non |
yes (under skull) |
very |
very |
non |
non |
cellular
extracellular microeelectrodes
intracellular microelectrode
neuropixels
optical
calcium imaging / fluorescence imaging
whole-brain light sheet imaging
voltage-sensitive dyes / voltage imaging
adaptive optics
fNRIS - like fMRI but cheaper, allows more immobility, slightly worse spatial res
oct - noninvasive - can look at retina (maybe find biomarkers of alzheimer’s)
fiber photometry - optical fiber implanted delivers excitation light
alteration
optogenetic stimulation
tms
genetically-targeted tms: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4846560/
local microstimulation with invasive electrodes
high-level
EEG/ECoG
MEG
fMRI/PET
molecular fmri (bartelle)
MRS
event-related optical signal = near-infrared spectroscopy
implantable
neural dust
1.12.4. general projects#
could a neuroscientist understand a deep neural network? - use neural tracing to build up wiring diagram / function
prediction-driven dimensionality reduction
deep heuristic for model-building
joint prediction of different input/output relationships
joint prediction of neurons from other areas
1.12.5. datasets#
-
MRNet: knee MRI diagnosis
springer 10k calcium imaging recording: https://figshare.com/articles/Recordings_of_ten_thousand_neurons_in_visual_cortex_during_spontaneous_behaviors/6163622
springer 2: 10k neurons with 2800 images
stringer et al. data
10000 neurons from visual cortex
neuropixels probes
10k neurons visual coding from allen institute
this probe has also been used in macaques
allen institute calcium imaging
An experiment is the unique combination of one mouse, one imaging depth (e.g. 175 um from surface of cortex), and one visual area (e.g. “Anterolateral visual area” or “VISal”)
predicting running, facial cues
dimensionality reduction
enforcing bottleneck in the deep model
how else to do dim reduction?
responses to 2800 images
overview: http://www.scholarpedia.org/article/Encyclopedia_of_computational_neuroscience
keeping up to date: https://sanjayankur31.github.io/planet-neuroscience/
lots of good data: http://home.earthlink.net/~perlewitz/index.html
connectome
fly brain: http://temca2data.org/
models
senseLab: https://senselab.med.yale.edu/
modelDB - has NEURON code
model databases: http://www.cnsorg.org/model-database
comp neuro databases: http://home.earthlink.net/~perlewitz/database.html
raw misc data
crcns data: http://crcns.org/
visual cortex data (gallant)
hippocampus spike trains
allen brain atlas: http://www.brain-map.org/
includes calcium-imaging dataset: http://help.brain-map.org/display/observatory/Data+-+Visual+Coding
wikipedia page: https://en.wikipedia.org/wiki/List_of_neuroscience_databases
human fMRI datasets: https://docs.google.com/document/d/1bRqfcJOV7U4f-aa3h8yPBjYQoLXYLLgeY6_af_N2CTM/edit
Kay et al 2008 has data on responses to images
calcium imaging for spike sorting: http://spikefinder.codeneuro.org/