When employing an evolutionary algorithm to optimize a neural networks architecture, developers face the added challenge of tuning the evolutionary algorithm's own hyperparameters - population size, mutation rate, cloning rate, and number of generations. This paper introduces Neuvo Ecological Neural Architecture Search (ENAS), a novel method that incorporates these evolutionary parameters directly into the candidate solutions' phenotypes, allowing them to evolve dynamically alongside architecture specifications. Experimental results across four binary classification datasets demonstrate that ENAS not only eliminates manual tuning of evolutionary parameters but also outperforms competitor NAS methodologies in convergence speed (reducing computational time by 18.3%) and accuracy (improving classification performance in 3 out of 4 datasets). By enabling "greedy individuals" to optimize resource allocation based on fitness, ENAS provides an efficient, self-regulating approach to neural architecture search.

In population genetics, a common problem is the inference of evolutionary events and parameters given some observed DNA sequencing data. This is typically done by leveraging genetic simulators based on the coalescence model. For example, in approximate Bayesian Computation (ABC) one can infer the posterior distribution of the evolutionary parameter of interest by (i) drawing its value from a prior, (ii) generate population genetic data from a simulator using the drawn parameter value and (iii) weight the importance of the sample based on the similarity between the simulated and the real data. Similarity is typically defined in terms of a pre-chosen set of summary statistics. The authors propose an inference strategy that does not rely on any choice of summary statistics.

We propose a dynamic joint sentiment-topic model (dJST) which allows the detection and tracking of views of current and recurrent interests and shifts in topic and sentiment. Both topic and sentiment dynamics are captured by assuming that the current sentiment-topic specific word distributions are generated according to the word distributions at previous epochs. We derive efficient online inference procedures to sequentially update the model with newly arrived data and show the effectiveness of our proposed model on the Mozilla add-on reviews crawled between 2007 and 2011.