Professor Chris Eliasmith gave a guest presentation on some mechanisms of encoding information within spiking neural networks. Spatial Semantic Pointers are an extension of the semantic pointer architecture which is a form of vector symbolic architecture where discrete values for a set of attributes are encoded as vectors and "bound" to the basis vector corresponding to the attribute using some operator (in this case circular convolution); the data can then be retrieved with the inverse operation. In the Spatial Semantic Pointers, this encoding is extended to continuous data and can be manipulated in several ways. Legendre Memory Units are a framework for approximating an ideal time delay for input data, which has been shown to be a useful and resource-efficient replacement for LSTMs and other advanced recurrent neural network structures.