Difference between revisions of "Hierarchical Temporal Memory (HTM)"
m |
m |
||
| Line 33: | Line 33: | ||
<youtube>ZFazR5yqesk</youtube> | <youtube>ZFazR5yqesk</youtube> | ||
<youtube>u-BIsnN-xxM</youtube> | <youtube>u-BIsnN-xxM</youtube> | ||
| + | <youtube>tg_m_LxxRwM</youtube> | ||
= Study of the Brain and Development of Intelligent Machines | Jeff Hawkins = | = Study of the Brain and Development of Intelligent Machines | Jeff Hawkins = | ||
Revision as of 20:20, 19 August 2020
YouTube search... ...Google search
- Temporal Computing
- Hierarchical Clustering; Agglomerative (HAC) & Divisive (HDC)
- Hierarchical Cluster Analysis (HCA)
- Capabilities
- Clustering
- An Alternative to Deep Learning? Guide to Hierarchical Temporal Memory (HTM) for Unsupervised Learning | Tavish Srivastava
- Numenta HTM School
- Hierarchical Temporal Memory for Real-time Anomaly Detection | Ihor Bobak
- Numentra - Where Neuroscience Meets Machine Intelligence
- Hierarchical Temporal Memory (HTM) School | Matt Taylor - Numentra
- Numenta.org
- Biological and Machine Intelligence (BAMI)
- Anomaly Detection
HTM are learning algorithms that can store, learn, infer, and recall high-order sequences. Unlike most other machine learning methods, HTM continuously learns (in an unsupervised process) time-based patterns in unlabeled data. HTM is robust to noise, and has high capacity (it can learn multiple patterns simultaneously). Wikipedia
Study of the Brain and Development of Intelligent Machines | Jeff Hawkins
