m8ta
You are not authenticated, login. 

{1552}  
Modularizing Deep Learning via Pairwise Learning With Kernels
I think in general this is an important result, even if its not wholly unique / somewhat anticipated (it's a year old at the time of writing). Modular training of neural networks is great for efficiency, parallelization, and biological implementations! Transport of weights between layers is hence nonessential. Classes still are, but I wonder if temporal continuity can solve some of these problems? (There is plenty of other effort in this area  see also {1544})  
{1547}  
MetaLearning Update Rules for Unsupervised Representation Learning
This is a clearlywritten, easy to understand paper. The results are not highly compelling, but as a first set of experiments, it's successful enough. I wonder what more constraints (fewer parameters, per the genome), more options for architecture modifications (e.g. different feedback schemes, per neurobiology), and a blackbox optimization algorithm (evolution) would do?  
{1528}  
Discovering hidden factors of variation in deep networks
 
{1455}  
Conducting credit assignment by aligning local distributed representations
Lit review.
 
{1426}  
Training neural networks with local error signals
 
{1432}  
Direct Feedback alignment provides learning in deep neural nets
 
{1423}  
PMID27824044 Random synaptic feedback weights support error backpropagation for deep learning.
Our proof says that weights W0 and W evolve to equilibrium manifolds, but simulations (Fig. 4) and analytic results (Supple mentary Proof 2) hint at something more specific: that when the weights begin near 0, feedback alignment encourages W to act like a local pseudoinverse of B around the error manifold. This fact is important because if B were exactly W + (the Moore Penrose pseudoinverse of W ), then the network would be performing GaussNewton optimization (Supplementary Proof 3). We call this update rule for the hidden units pseudobackprop and denote it by âˆ†hPBP = W + e. Experiments with the linear net work show that the angle, âˆ†hFA ]âˆ†hPBP quickly becomes smaller than âˆ†hFA ]âˆ†hBP (Fig. 4b, c; see Methods). In other words feedback alignment, despite its simplicity, displays elements of secondorder learning. 