Backpropagation and the brain
The backpropagation of error (backprop) algorithm is frequently used to train deep neural networks in machine learning, but it has not been viewed as being implemented by the brain. In this Perspective, however, Lillicrap and colleagues argue that the key principles underlying backprop may indeed have a role in brain function.
Subjects Cortex Learning algorithms Long-term potentiation Network models Neurophysiology Abstract During learning, the brain modifies synapses to improve behaviour. In the cortex, synapses are embedded within multilayered networks, making it difficult to determine the effect of an individual synaptic modification on the behaviour of the system. The backpropagation algorithm solves this problem in deep artificial neural networks, but historically it has been viewed as biologically problematic. Nonetheless, recent developments in neuroscience and the successes of artificial neural networks have
related reading
- Artificial Neural Nets Finally Yield Clues to How Brains Learn | Quanta Magazinequantamagazine.org
- So how does learning work?cs.mcgill.ca
- Yes you should understand backprop | by Andrej Karpathy | Mediumkarpathy.medium.com
- Don't Mess with Backprop: Doubts about Biologically Plausible Deep Learningevjang.com
- Inferring neural activity before plasticity as a foundation for learning beyond backpropagation.mrcbndu.ox.ac.uk
- Neural networks and deep learningneuralnetworksanddeeplearning.com
- Backpropagation - Wikipediaen.wikipedia.org
- Neural networks and deep learningneuralnetworksanddeeplearning.com
- Calculus on Computational Graphs: Backpropagation -- colah's blogcolah.github.io
- A deep learning framework for neuroscience - PMCncbi.nlm.nih.gov
- Neuroscience is pre-paradigmatic. Consciousness is whytheintrinsicperspective.com
- Loss of plasticity in deep continual learning | Naturenature.com