# Research Papers

Foundational paper describing core HTM theory for sequence memory and its relationship to the neocortex. Written with a neuroscience perspective, the paper explains why neurons need so many synapses and how networks of neurons can form a powerful sequence learning mechanism.

Analysis of HTM sequence memory applied to various sequence learning and prediction problems. Written with a machine learning perspective, the paper contains some comparisons to statistical and Deep Learning techniques.

14th IEEE ICMLA 2015 - This paper discusses how we should think about anomaly detection for streaming applications. It introduces a new open-source benchmark for detecting anomalies in real-time, time-series data.

Much of the worlds data is streaming, time-series data, where anomalies give significant information in critical situations. Yet detecting anomalies in streaming data is a difficult task, requiring detectors to process data in real-time, and learn while simultaneously making predictions.

This paper describes a mathematical model for quantifying the benefits and limitations of sparse representations in neurons and cortical networks.

An earlier version of the above submission, this paper applies our mathematical model of sparse representations to practical HTM systems.

Hierarchical Temporal Memory (HTM) is a biologically inspired machine intelligence technology that mimics the architecture and processes of the neocortex. In this white paper we describe how to encode data as Sparse Distributed Representations (SDRs) for use in HTM systems. We explain several existing encoders, which are available through the open source project called NuPIC, and we discuss requirements for creating encoders for new types of data.

Recently there has been much interest in building custom hardware implementations of HTM systems. This paper discusses one such scenario, and shows how to port HTM algorithms to analog hardware platforms such as the one developed by the Human Brain Project.