Random synaptic feedback weights support error backpropagation for deep learning

Lillicrap, Timothy P.; Cownden, Daniel; Tweed, Douglas; Akerman, Colin J.

doi:10.1038/ncomms13276

Cited by 588 publications

(736 citation statements)

References 52 publications

Supporting

Mentioning

685

Contrasting

Order By: Relevance

“…Some of the criticisms include the use in backpropagation of symmetrical weight for the forward inference and backward error propagation phase, the relative paucity of supervised signals and the clear and strong unsupervised basis of much learning. Recent research has shown that the symmetrical weight requirement is not a specific requirement (Lillicrap, Cownden, Tweed, & Akerman, 2016). Roelfsema and van Ooyen (2005) already showed that an activation feedback combined with a broadly distributed, dopamine-like errordifference signal can on average learn error-backpropagation in a reinforcement learning setting.…”

Section: 1mentioning

confidence: 99%

Visual pathways from the perspective of cost functions and multi-task deep neural networks

Scholte

Losch

Ramakrishnan

et al. 2018

Cortex

View full text Add to dashboard Cite

Deep learning Cost functions RepresentationsVisual processing a b s t r a c t Vision research has been shaped by the seminal insight that we can understand the higher-tier visual cortex from the perspective of multiple functional pathways with different goals. In this paper, we try to give a computational account of the functional organization of this system by reasoning from the perspective of multi-task deep neural networks. Machine learning has shown that tasks become easier to solve when they are decomposed into subtasks with their own cost function. We hypothesize that the visual system optimizes multiple cost functions of unrelated tasks and this causes the emergence of a ventral pathway dedicated to vision for perception, and a dorsal pathway dedicated to vision for action.To evaluate the functional organization in multi-task deep neural networks, we propose a method that measures the contribution of a unit towards each task, applying it to two networks that have been trained on either two related or two unrelated tasks, using an identical stimulus set. Results show that the network trained on the unrelated tasks shows a decreasing degree of feature representation sharing towards higher-tier layers while the network trained on related tasks uniformly shows high degree of sharing.We conjecture that the method we propose can be used to analyze the anatomical and functional organization of the visual system and beyond. We predict that the degree to which tasks are related is a good descriptor of the degree to which they share downstream cortical-units.

show abstract

Section: 1mentioning

confidence: 99%

Visual pathways from the perspective of cost functions and multi-task deep neural networks

Scholte

Losch

Ramakrishnan

et al. 2018

Cortex

View full text Add to dashboard Cite

show abstract

“…Although, previous work (Lee et al, 2016;Lillicrap et al, 2016;O'Connor and Welling, 2016) overcomes some of the fundamental difficulties of gradient BP listed above in spiking networks, here we tackle all of the key difficulties using eventdriven random BP (eRBP), a synaptic plasticity rule for deep spiking neural networks achieving classification accuracies that are similar to those obtained in artificial neural networks, potentially running on a fraction of the energy budget with dedicated neuromorphic hardware.…”

Section: Introductionmentioning

confidence: 99%

Event-driven random backpropagation: Enabling neuromorphic deep learning machines

Neftci

Augustine

Sauseng

et al. 2017

2017 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

An ongoing challenge in neuromorphic computing is to devise general and computationally efficient models of inference and learning which are compatible with the spatial and temporal constraints of the brain. One increasingly popular and successful approach is to take inspiration from inference and learning algorithms used in deep neural networks. However, the workhorse of deep learning, the gradient descent Gradient Back Propagation (BP) rule, often relies on the immediate availability of network-wide information stored with high-precision memory during learning, and precise operations that are difficult to realize in neuromorphic hardware. Remarkably, recent work showed that exact backpropagated gradients are not essential for learning deep representations. Building on these results, we demonstrate an event-driven random BP (eRBP) rule that uses an error-modulated synaptic plasticity for learning deep representations. Using a two-compartment Leaky Integrate & Fire (I&F) neuron, the rule requires only one addition and two comparisons for each synaptic weight, making it very suitable for implementation in digital or mixed-signal neuromorphic hardware. Our results show that using eRBP, deep representations are rapidly learned, achieving classification accuracies on permutation invariant datasets comparable to those obtained in artificial neural network simulations on GPUs, while being robust to neural and synaptic state quantizations during learning.

show abstract

“…Three are highlighted here, see Section 3.5, and especially Sections 3.6 and 3.7. Other algorithms where the Response graphs do not simply implement backprop include difference target propagation (Lee et al, 2015) and feedback alignment (Lillicrap et al, 2014) [both discussed briefly in Section 3.7] and truncated backpropagation through time (Elman, 1990;Williams and Peng, 1990;Williams and Zipser, 1995), where a choice is made about where to cut backprop short. Examples where the query and response graph differ are of particular interest, since they point toward more general classes of deep learning algorithms.…”

Section: Grammars For Gamesmentioning

confidence: 99%

“…Two recent alternatives to backprop that also do not rely on backpropagating exact gradients are target propagation (Lee et al, 2015) and feedback alignment (Lillicrap et al, 2014). Target propagation makes do without gradients by implementing autoencoders at each layer.…”

Section: R 4 (Biological Plausibility Of Kickback)mentioning

confidence: 99%

Grammars for Games: A Gradient-Based, Game-Theoretic Framework for Optimization in Deep Learning

Balduzzi

2016

Front. Robot. AI

View full text Add to dashboard Cite

Deep learning is currently the subject of intensive study. However, fundamental concepts such as representations are not formally defined -researchers "know them when they see them" -and there is no common language for describing and analyzing algorithms. This essay proposes an abstract framework that identifies the essential features of current practice and may provide a foundation for future developments. The backbone of almost all deep learning algorithms is backpropagation, which is simply a gradient computation distributed over a neural network. The main ingredients of the framework are, thus, unsurprisingly: (i) game theory, to formalize distributed optimization; and (ii) communication protocols, to track the flow of zeroth and first-order information. The framework allows natural definitions of semantics (as the meaning encoded in functions), representations (as functions whose semantics is chosen to optimized a criterion), and grammars (as communication protocols equipped with first-order convergence guarantees). Much of the essay is spent discussing examples taken from the literature. The ultimate aim is to develop a graphical language for describing the structure of deep learning algorithms that backgrounds the details of the optimization procedure and foregrounds how the components interact. Inspiration is taken from probabilistic graphical models and factor graphs, which capture the essential structural features of multivariate distributions.

show abstract

Random synaptic feedback weights support error backpropagation for deep learning

Cited by 588 publications

References 52 publications

Visual pathways from the perspective of cost functions and multi-task deep neural networks

Visual pathways from the perspective of cost functions and multi-task deep neural networks

Event-driven random backpropagation: Enabling neuromorphic deep learning machines

Grammars for Games: A Gradient-Based, Game-Theoretic Framework for Optimization in Deep Learning

Contact Info

Product

Resources

About