Using algorithms derived from its neuroscience research, Numenta announced today it has achieved dramatic performance improvements on inference tasks in deep learning networks without any loss in accuracy.
A new paper published in Frontiers in Neural Circuits titled, A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex, proposes a new way to understand how the neocortex works. Numenta’s Thousand Brains Theory of Intelligence offers significant implications for the fields of neuroscience and artificial intelligence.
In a new research paper titled A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex, Numenta researchers propose a broad framework for understanding what the neocortex does and how it works. Numenta’s Thousand Brains Theory of Intelligence offers significant implications for the fields of neuroscience and artificial intelligence.
In the Numenta Columns paper, they proposed a theory for how the brain learns models of objects through movement. The theory is an important piece of their goal to reverse-engineer the neocortex. In a blog titled “The Secret to Strong AI” on Medium, Jeff Hawkins describes the importance of the new theory to AGI.
Neuroscience and machine intelligence researchers at Numenta reveal Hierarchical Temporal Memory (HTM)’s results on real-time anomaly detection. They have described the technique in a new peer-reviewed paper, Unsupervised real-time anomaly detection for streaming data, published in a special issue of Neurocomputing.