Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
1. Introduction Hyperdimensional (HD) computing, also known as Vector Symbolic Architectures (Gayler, 2003; Kanerva, 2009; Kleyko et al., 2022c,d), with origins in Holographic Reduced Representation (Plate, 1994a, 1995), is an approach to perform computations using vectors that contain many (in order of at least hundreds) of components. In HD computing, each basic concept within a domain is associated with a single vector.
1. Introduction Artificial intelligence (AI) has shown impressive abilities in various tasks such as computer vision, natural language processing, and decision making. For example, AlphaGo Zero defeated the world champion of the game of Go (Silver et al., 2017). However, the power consumption of AlphaGo Zero is about 1kW (Frenkel et al., 2021), which is 50× higher than the 20W power budget of the human brain (Roy et al., 2019).
Introduction Learning requires assigning credit to each neuron for its contribution to the final output (Bengio et al., 2015; Lillicrap et al., 2016). How a neuron determines its contribution is known as the credit assignment problem. In particular, the training of deep neural networks is based on error back-propagation, which uses a feedback pathway to transmit information to calculate error signals in the hidden layers.
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
