On Intelligence

By J. Hawkins, S. Blakeslee. 2004

1,402 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.

Citations in the corpus

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “l., 2015; Silver et al., 2016), have highlighted the importance of learning from large input-output data and extensive training. Other areas of cognition such as the capabilities to make predictions (Hawkins and Blakeslee, 2007), to establish associations (Rescorla, 2014) and to regulate behaviors (”
Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images (2015, background): “Humans reliably use these predictions for planning their actions, making everyday decisions, and even correcting visual interpretations [15].”
A Generalist Agent (2022, methodology): “This has motivated arguments that we may only need one algorithm or model to build intelligence (Hawkins & Blakeslee, 2004).”
Toward an Integration of Deep Learning and Neuroscience (2016, background): “It has been suggested that the hippocampus can be thought of as the top of the cortical hierarchy (Hawkins and Blakeslee, 2007), responsible for handling and remembering information that could not be fully explained by lower levels of the hierarchy.”
Multi-timescale nexting in a reinforcement learning robot (2011, background): “The ability to predict and anticipate has often been proposed as a key part of intelligence (e.g., see Tolman 1951, Hawkins & Blakeslee 2004, Butz et al. 2003, Wolpert et al. 1995, Clark in press).”
A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex (2005, background): “Its emphasis is thus somewhat different with respect to ideas related to prediction-verification recursions – an approach known in AI as “hypothesis-verification” (see among others, [Hawkins and Blakeslee, 2002; Mumford, 1996; Rao and Ballard, 1999]).”
A dynamical model of general intelligence: the positive manifold of intelligence by mutualism. (2006, background): “Whereas a number of authors have proposed this idea of reciprocal causation (e.g., Ceci, 1990; Jensen, 1998; Scarr & McCartney, 1983), Dickens and Flynn (2001) used a formal model to show that this idea may explain the IQ paradox.”
Storytelling as an Instructional Method: Definitions and Research Questions. (2009, background): “It is suggested that this aides our ability to prepare for and act in future contexts (Hawkins & Blakeslee, 2004).”
A Machine Learning Perspective on Predictive Coding with PAQ (2011, background): “o several domains including language modeling and unsupervised learning of audio and video sequences. Some researchers have argued that sequence prediction is key to understanding human intelligence (Hawkins and Blakeslee, 2005). The close connections between sequence prediction and data compression”
Evaluating Real-Time Anomaly Detection Algorithms -- The Numenta Anomaly Benchmark (2015, methodology): “y described below. The HTM detector (developed by Numenta and the authors) is based on Hierarchical Temporal Memory (HTM), a machine intelligence technology inspired by the structure of the neocortex [17, 18, 19]. Given a real-time data stream ⋯,��−2,��−1,��,��+1,��+2,⋯, the algorithm models the 1 C”
Memory, Attention, and Choice* (2020, unknown): “These ideas are also related to an emerging paradigm in the neuroscience of sensory perception, in which the brain spontaneously forms predictions of the environment known as mental representations (e.g., Hawkins and Blakeslee 2004; Clark 2013).”