One of the common criticisms of Deep Learning is it's training algorithms, back-propagation of error (back-prop), has no biologically plausible implementation, despite evidence of something like it occurring in the brain. The default implementation is considered biologically implausible due to it's reliance on bi-directional synapses. However, there's been a lot of publications published showing implementations that should be plausible. Specifically, from section 2.2.2 of the review "Towards an integration of deep learning and neuroscience" and some discussion I've had:
- Random synaptic feedback weights support error backpropagation for deep learning
- Direct Feedback Alignment (related to the previous random weights idea) and it's inclusion in the Superspike algorithm
- Deep learning with segregated dendrites
- Spike timing dependent plasticity (STDP) with iterative inference and target propagation which is based off Difference Target Propagation
- Kickback from "Kickback cuts Backprop's red-tape: Biologically plausible credit assignment in neural networks"
- Generalized Recirculation from "Biologically Plausible Error-driven Learning using Local Activation Differences: The Generalized Recirculation Algorithm"
- Contrastive Hebbian Learning from "Equivalence of backpropagation and contrastive Hebbian learning in a layered network"
- Complex neurons from "Supervised and unsupervised learning with two sites of synaptic integration"
- Using an attention mechanism from "A Biologically Plausible Learning Rule for Deep Learning in the Brain"
- Layer-specific target from "GAIT-prop: A biologically plausible learning rulederived from backpropagation of error"
Are any of these implementable in spiking neurons, able to scale to more than two layers and have been shown to work on normal Deep Learning benchmarks such as MNIST or ImageNet?