In behavioural ecology, animal social networks are used to answer a wide variety of questions. However, unlike in the analysis of human social networks, we can’t ask animals what their social preferences are. Instead we have to estimate them based on observable events like spatial associations or interactions. This means Read more…
Background Traditional convolutional neural networks (CNNs) have been hugely successful on a number of problems. In the case of visual processing, they work by sliding small filters (or kernels) across each pixel and its neighbours, and producing a single value. The weights of these filters are trainable, which allows the Read more…
Github repository: github.com/JHart96/keras_elmo_embedding_layer. ELMo embeddings Pre-trained word embeddings have been highly successful in numerous natural language processing tasks. Traditional word embeddings are essentially lookup tables mapping a word to its corresponding feature vector. As a result, the context of a word is not taken into account when generating its embedding. Allen Read more…