Hyperdimensional Computing is an emergent model of computation where all objects are represented in high-dimensional vectors. This model includes a well-defined set of arithmetic operations that produce new highdimensional vectors, which, in addition to represent basic entities, can also represent more complex data structures such as sets, relations and sequences. This paper presents a method for sequence prediction using Hyperdimensional Computing and the Sparse Distributed Memory model. The proposed method is based on the encoding, storage and retrieval of sequence vectors, which store the k consecutive vectors of a sequence. The next element of a sequence is selected by taking into account the current, as well as the k immediate preceding elements of the sequence. Each vector is associated to a sequence vector that is stored in memory; the way in which each vector is associated to its sequence vectors is the main contribution of this paper. We present experimental results for the encoding and prediction of randomly generated sequences and the results indicate that the method performs correct predictions.

Hyperdimensional computing is an emergent model of computation based on the manipulation of high-dimensional vectors which are used not only to represent variables and values, but also to represent complex structures such as relations, sets and sequences. All vectors in the model are always the same size either if they represent a single concept or a sequence of objects. Hyperdimensional computing uses reduced representations, since there is a compression process to encode complex structures while maintaining the same size on the output vector. In this paper we explore the storing capacity of hyperdimensional vectors that encode semantic feature norms. We describe a method for encoding and retrieving feature information of concrete concepts and present experimental results of the successful retrieval of such features.

No abstract