• Corpus ID: 18228891

Intelligent Predictions : an empirical study of the Cortical Learning Algorithm

  title={Intelligent Predictions : an empirical study of the Cortical Learning Algorithm},
  author={Michael Galetzka},
Intelligent Predictions: an empirical study of the Cortical Learning Algorithm The theory of Hierarchical Temporal Memory (HTM) created a new approach to machine learning for time-series prediction and anomaly detection. A subset of the theoretical framework was implemented in the open source framework nupic by Numenta. With the help of this framework, an empirical study was conducted to assess the capabilities and limitations of HTM. The results indicate that the performance is comparable to… 
Application of cortical learning algorithms to movement classification towards automated video forensics
  • A. Alshaikh
  • Computer Science
    International Journal of Computer Applications Technology and Research
  • 2019
A novel CLA-based movement classification algorithm has been proposed and devised to classify the movements of moving objects in realistic video surveillance scenarios, and the test results have been evaluated and compared against several state-of-the-art anomaly detection algorithms.
Automatic Detection of Fake News in Social Media using Contextual Information
This thesis investigates how using contextual and network data may be used as a detection system for news articles or other information pieces, Either as a standalone system or part of a bigger, hybrid solution.
Common sense validation and reasoning using Natural Language Processing
The results of this paper show that a combination of more than one technique is better suited for the purpose of classifications.
Genre Classification of Spotify Songs using Lyrics , Audio Previews , and Album Artwork
Three different types of data are used to train three models (a Recurrent Neural Network, k-Nearest Neighbors, and Naive Bayes) and the outputs of the three are again combined to classify a given song.


Hierarchical Bayesian reservoir memory
The model is a hierarchical Bayesian structure that uses Reservoir Computing methods as the state-of-the-art and the most biological plausible Temporal Sequence Processing method for online and unsupervised learning.
How the brain might work: a hierarchical and temporal model for learning and recognition
Algorithms and networks that combine hierarchical and temporal learning with Bayesian inference for pattern recognition and a generative model for HTMs are developed, which enables the generation of synthetic data from HTM networks.
Input Feedback Networks: Classification and Inference Based on Network Structure
This new model of interacting neuron-like units, called Input Feedback Networks, is promising for future contributions to integrated human-level intelligent applications due to its flexibility, dynamics and structural similarity to natural neuronal networks.
Dynamic bayesian networks: representation, inference and learning
This thesis will discuss how to represent many different kinds of models as DBNs, how to perform exact and approximate inference in Dbns, and how to learn DBN models from sequential data.
Object Categorization Using VFA-generated Nodemaps and Hierarchical Temporal Memories
A novel object categorization method based on statistical properties of nodes -derived from the VFA model -and hierarchical temporal memories is proposed, which shows that categorization based on the statistics of nodes seems to yield higher success rates.
Application of Numenta® Hierarchical Temporal Memory for land-use classification
Hierarchical Temporal Memory is a theory that explains how humans, and mammals in general, can recognise images despite changes in location, size and lighting conditions, and in the presence of deformations and large amounts of noise.
Recurrent neural networks and robust time series prediction
A robust learning algorithm is proposed and applied to recurrent neural networks, NARMA(p,q), which show advantages over feedforward neural networks for time series with a moving average component and are shown to give better predictions than neural networks trained on unfiltered time series.
Transfer Learning and Intelligence: an Argument and Approach
This paper presents transfer learning, where knowledge from a learned task can be used to significantly speed up learning in a novel task, as the key to achieving the learning capabilities necessary for general intelligence.
A neural network model of spatio-temporal pattern recognition, recall, and timing
  • Christian Mannes
  • Computer Science
    [Proceedings 1992] IJCNN International Joint Conference on Neural Networks
  • 1992
The author describes the design of a self-organizing, hierarchical network model of unsupervised serial learning. The model learns to recognize, store, and recall sequences of unitized patterns,
Time in Connectionist Models
The purpose of this chapter is to present the main aspects of this research area and to review the key connectionist architectures that have been designed for solving temporal problems.