Why neuroscience?¶
History of neuroscience and machine learning¶
- McCulloch and Pitts (1943) “A logical calculus of the ideas immanent in nervous activity”
- Von Neumann (1945) “First draft of a report on the EDVAC”
- Rosenblatt (1958) “The perceptron: A probabilistic model for information storage and organization in the brain”
- Goodman et al. (2013) “Decoding neural responses to temporal cues for sound localization”
- Minsky and Papert (1969) “Perceptrons: An Introduction to Computational Geometry”
- Larsen et al. (2022) “Towards a more general understanding of the algorithmic utility of recurrent connections”
- Rumelhart et al. (1986) “Learning representations by back-propagating errors”
- Introduction to neural networks and backpropagation by 3Blue1Brown (excellent, easy to follow YouTube series)
- Lillicrap et al. (2016) “Random synaptic feedback weights support error backpropagation for deep learning”
- Lillicrap et al. (2020) “Backpropagation and the brain”
- Hubel and Wiesel (1959) “Receptive fields of single neurones in the cat’s striate cortex”
- Hubel and Wiesel (1962) “Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex”
- Fukushima (1980) “Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position”
- LeCun et al. (1989) “Backpropagation Applied to Handwritten Zip Code Recognition”
- LeCun et al. (1998) “Gradient-based learning applied to document recognition”
- Yamins et al. (2014) “Performance-optimized hierarchical models predict neural responses in higher visual cortex”
- Kell et al. (2018) “A Task-Optimized Neural Network Replicates Human Auditory Behavior, Predicts Brain Responses, and Reveals a Cortical Processing Hierarchy”
- Schrimpf et al. (2020) “Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like?”
- Brain-Score website
- Jacob et al. (2021) “Qualitative similarities and differences in visual object representations between brains and deep networks”
- Weerts et al. (2022) “The Psychometrics of Automatic Speech Recognition”
- Adolfi et al. (2023) “Successes and critical failures of neural networks in capturing human-like speech recognition”
- Thorndike (1898) “Animal intelligence: An experimental study of the associative processes in animals”
- Sutton and Barto (2018) “Reinforcement Learning: An Introduction”
- Turing (1948) “Intelligent Machinery”
- Hassabis et al. (2017) " Neuroscience-Inspired Artificial Intelligence"
- Zador et al. (2023) “Catalyzing next-generation Artificial Intelligence through NeuroAI”
- Doerig et al. (2023) “The neuroconnectionist research programme”
- Patrick Mineault “NeuroAI archive” and website
Challenges for ML and neuroscience¶
- AlphaGo The Movie
- Silver et al. (2017) “Mastering the game of Go without human knowledge”
- Vicarious 2016 on Schema networks (broken videos) (and preprint)
- Tsividis et al. (2017) “Human learning in Atari”
- Goodfellow et al. (2014) “Explaining and Harnessing Adversarial Examples”
- Geirhos et al. (2019) “ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness”
- OpenAI: Multimodal neurons in artificial neural networks
- Cramer et al. (2022) “The Heidelberg Spiking Data Sets for the Systematic Evaluation of Spiking Neural Networks”
- McCulloch, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The Bulletin of Mathematical Biophysics, 5(4), 115–133. 10.1007/bf02478259
- Rosenblatt, F. (1958). The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65(6), 386–408. 10.1037/h0042519
- Goodman, D. F., Benichoux, V., & Brette, R. (2013). Decoding neural responses to temporal cues for sound localization. eLife, 2. 10.7554/elife.01312
- Minsky, M., & Papert, S. A. (2017). Perceptrons: An Introduction to Computational Geometry. The MIT Press. 10.7551/mitpress/11301.001.0001
- Larsen, B. W., & Druckmann, S. (2022). Towards a more general understanding of the algorithmic utility of recurrent connections. PLOS Computational Biology, 18(6), e1010227. 10.1371/journal.pcbi.1010227