m8ta
use https for features. 

{1528}  
Discovering hidden factors of variation in deep networks
 
{1527} 
ref: 0
tags: inductive logic programming deepmind formal propositions prolog
date: 11212020 04:07 gmt
revision:0
[head]


Learning Explanatory Rules from Noisy Data
 
{1490}  
PMID21527931 Twophoton absorption properties of fluorescent proteins
 
{1526} 
ref: 0
tags: neuronal assemblies maass hebbian plasticity simulation austria fMRI
date: 10272020 21:39 gmt
revision:0
[head]


PMID32381648 A model for structured information representation in neural networks in the brain
 
{1525}  
Why deep learning works even though it shouldn't, instigated a fun thread thinking about "complexity of model" vs "complexity of solution".
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Stabilizing the lottery ticket hypothesis
Identifying and attacking the saddle point problem in highdimensional nonconvex optimization Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited
Random deep neural networks are biased towards simple functions
Reconciling modern machine learning practice and the biasvariance tradeoff
 
{1524} 
ref: 2020
tags: replay hippocampus variational autoencoder
date: 10112020 04:09 gmt
revision:1
[0] [head]


Braininspired replay for continual learning with artificial neural networks
 
{1523} 
ref: 0
tags: tennenbaum compositional learning character recognition oneshot learning
date: 09292020 03:44 gmt
revision:1
[0] [head]


Oneshot learning by inverting a compositional causal process
 
{1522}  
Schema networks: zeroshot transfer with a generative causal model of intuitive physics
 
{1521} 
ref: 2005
tags: dimensionality reduction contrastive gradient descent
date: 09132020 02:49 gmt
revision:2
[1] [0] [head]


Dimensionality reduction by learning and invariant mapping
 
{1520}  
PMID15142952 Visual binding through reentrant connectivity and dynamic synchronization in a brainbased device
 
{1519}  
Neuralink progress update August 28 2020 Some commentary. The good:
The mixed:
 
{1417} 
ref: 0
tags: synaptic plasticity 2photon imaging inhibition excitation spines dendrites synapses 2p
date: 08142020 01:35 gmt
revision:3
[2] [1] [0] [head]


PMID22542188 Clustered dynamics of inhibitory synapses and dendritic spines in the adult neocortex.
 
{1478} 
ref: 2013
tags: 2p two photon STED super resolution microscope synapse synaptic plasticity
date: 08142020 01:34 gmt
revision:3
[2] [1] [0] [head]


PMID23442956 TwoPhoton Excitation STED Microscopy in Two Colors in Acute Brain Slices
PMID29932052 Chronic 2PSTED imaging reveals high turnover of spines in the hippocampus in vivo  
{1518}  
PMID31780899 Single Synapse LTP: A matter of context?
 
{1504}  
Various GEVIs invented and evolved: AceFRET sensors
Arch and Mac rhodopsin sensors
VSD  FP sensors
 
{1517}  
PMID26621426 Causal Inference and Explaining Away in a Spiking Network
 
{1516}  
Inductive representation learning on large graphs
This is a wellput together paper, with some proofs of convergence etc  but it still feels only lightly tested. As with many of these papers, could benefit from a positive control, where the generating function is known & you can see how well the algorithm discovers it. Otherwise, the structure / algorithm feels rather intuitive; surprising to me that it was not developed before the matrix factorization methods. Worth comparing this to word2vec embeddings, where local words are used to predict the current word & the resulting vector in the neckdown of the NN is the representation.  
{1515}  
SuperPhotostable PhospholeBased Dye for MultipleAcquisition Stimulated Emission Depletion Imaging
 
{1513}  
Spent a while this evening reading about Qualified Immunity  the law that permits government officials (e.g. police officers) immunity when 'doing their jobs'. It's perhaps one root of the George Floyd / racism protests, as it has set a precedent that US police can be violent and get away with it. (This is also related to police unions and collective liability loops... anyway) The supreme court has the option to take cases challenging the constitutionality of Qualified Immunity, which many on both sides of the political spectrum want them to do. It 'got' this power via Marbury vs. Madison. M v. M is selfreferential genius:
As a person curious how systems gain complexity and feedback loops ... so much nerdgasm.  
{1512} 
ref: 0
tags: rutherford journal computational theory neumann complexity wolfram
date: 05052020 18:15 gmt
revision:0
[head]


The Structures for Computation and the Mathematical Structure of Nature
