How the brain might work: a hierarchical and temporal model for learning and recognition

By Dileep George. 2008

190 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Li Deng
2. Zeyuan Allen-Zhu
3. Yuanzhi Li
4. Yoshua Bengio
5. Dong Yu
6. Bo Chen
7. Ruslan Salakhutdinov
8. Dacheng Tao

Citations in the corpus

• Deep Learning: Methods and Applications (2014, background): “In a similar vein, the human visual system is also hierarchical in nature, mostly in the perception side but interestingly also in the “generation” side [43, 126, 287]).”
• A tutorial survey of architectures, algorithms, and applications for deep learning (2014, background): “It is also useful to point out that the model of hierarchical temporal memory (HTM, [17, 128, 130] is another variant and extension of the CNN.”
• Backward Feature Correction: How Deep Learning Performs Deep Learning (2020, background): “There is strong evidence that human brains perform learning in hierarchically organized circuits, which is the key for us to learn new concept class with relatively few examples [24].”
• Towards a Mathematical Theory of Cortical Micro-circuits (2009, background): “More details about the training methods and the learned coincidence patterns and Markov chains can be found in [8].”
• Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier] (2010, background): “chical Temporal Memory (HTM) developed at the Numenta Corporation [30] [33].”
• Deep Learning for Time Series Anomaly Detection: A Survey (2022, unknown): “Autoencoders (AEs), also known as auto-associative neural networks [105], are widely used in MTS anomaly detection for their nonlinear dimensionality reduction capabilities [150, 203].”
• Deep Learning of Invariant Spatio-Temporal Features from Video (2010, methodology): “The choice of an alternating space-time architecture was influenced by George’s work [13], but the addition of joint space-time layers to this architecture is a straightforward extension.”
• Long Short Term Memory Networks for Anomaly Detection in Time Series (2015, background): “A notable instance of using hierarchical temporal processing for anomaly detection is the Hierarchical Temporal Memory (HTM) system that attempts to mimic the hierarchy of cells, regions, and levels in the neocortex [4].”