A critique of pure learning and what artificial neural networks can learn from animal brains
Recent gains in artificial neural networks rely heavily on large amounts of training data. Here, the author suggests that for AI to learn from animal brains, it is important to consider that animal behaviour results from brain connectivity specified in the genome through evolution, and not due to unique learning algorithms.
Download PDF Subjects Computer science Network models Abstract Artificial neural networks (ANNs) have undergone a revolution, catalyzed by better supervised learning algorithms. However, in stark contrast to young animals (including humans), training such networks requires enormous numbers of labeled examples, leading to the belief that animals must rely instead mainly on unsupervised learning. Here we argue that most animal behavior is not the result of clever learning algorithms—supervised or unsupervised—but is encoded in the genome. Specifically, animals are born with highly structured bra
Explore this link on the map →saved by
related reading
- So how does learning work?cs.mcgill.ca
- Human-like Neural Nets by Catapulting · Gwern.netgwern.net
- Zoom In: An Introduction to Circuitsdistill.pub
- Analogies between Biology and Deep Learning [rough note] -- colah's blogcolah.github.io
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- Inferring neural activity before plasticity as a foundation for learning beyond backpropagation.mrcbndu.ox.ac.uk
- A deep learning framework for neuroscience - PMCncbi.nlm.nih.gov
- Artificial Neural Nets Finally Yield Clues to How Brains Learn | Quanta Magazinequantamagazine.org
- https://io0.github.ioio0.github.io
- Building machines that learn and think like people | Behavioral and Brain Sciences | Cambridge Corecambridge.org
- Animals vs Ghosts – karpathykarpathy.bearblog.dev
- Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like? | bioRxivbiorxiv.org