While sentence simplification is an active research topic in NLP, its adjacent tasks of sentence complexification and same-level paraphrasing are not. To train models on all three tasks, we present two new unsupervised datasets. We compare these datasets, one labeled by a weak classifier and the other by a rule-based approach, with a single supervised dataset. Using these three datasets for training, we perform extensive experiments on both multitasking and prompting strategies. Compared to other systems trained on unsupervised parallel data, models trained on our weak classifier labeled dataset achieve state-of-the-art performance on the ASSET simplification benchmark. Our models also outperform previous work on sentence level targeting. Finally, we establish how a handful of Large Language Models perform on these tasks under a zero-shot setting.

We introduce Biomaker CA: a Biome Maker project using Cellular Automata (CA). In Biomaker CA, morphogenesis is a first class citizen and small seeds need to grow into plant-like organisms to survive in a nutrient starved environment and eventually reproduce with variation so that a biome survives for long timelines. We simulate complex biomes by means of CA rules in 2D grids and parallelize all of its computation on GPUs through the Python JAX framework. We show how this project allows for several different kinds of environments and laws of 'physics', alongside different model architectures and mutation strategies. We further analyze some configurations to show how plant agents can grow, survive, reproduce, and evolve, forming stable and unstable biomes. We then demonstrate how one can meta-evolve models to survive in a harsh environment either through end-to-end meta-evolution or by a more surgical and efficient approach, called Petri dish meta-evolution. Finally, we show how to perform interactive evolution, where the user decides how to evolve a plant model interactively and then deploys it in a larger environment. We open source Biomaker CA at: https://tinyurl.com/2x8yu34s .

Intelligence in this "clean room" environment can be defined with respect to accumulated systematic methods of reasoning. So a logic proof system can be defined to be more efficient at solving a mathematical task than a comparable human. The more civilization transitions into a virtualized world, the more likely humans will find synthetic minds that are'more intelligent'. Classical definitions of computation tend to favor sequential processes. A consequence is that more natural parallel processes such as evolution tend to be ignored. Therefore a properly informed definition of intelligence must take into account how to scale parallel cognition.

In the last few years, deep learning has solved seemingly intractable problems, boosting the hope to find approximate solutions to problems that now are considered unsolvable. Earthquake prediction, the Grail of Seismology, is, in this context of continuous exciting discoveries, an obvious choice for deep learning exploration. The artificial neural network (ANN) (shallow or deep) is rapidly rising as one of the most powerful go-to techniques not only in data science [LeCun et al., 2015; Jordan and Mitchell, 2016] but also for solving hard and intractable problems of Physics (e.g., many-body problem [Carleo and Troyer, 2017], chaotic systems [Pathak et al., 2018], high-dimensional partial differential equations [Han et al., 2018]). This is justified by the superior performance of ANNs in discovering complex patterns in very large datasets with the advantage of not requiring feature extraction or engineering, as data can be used directly to train the network with potentially great results. It comes as no surprise that machine learning at large -- including ANNs -- has become popular in Statistical Seismology [Kong et al., 2019] and gives fresh hope for earthquake prediction [Rouet-Leduc et al., 2017; DeVries et al., 2018].

Research in neurally-based machine (i.e. computational) systems is expanding. “Reverse-engineered” models of brain-like structures are viable candidates for developing increasing complexification (via generatively encoded “intelligence”) that could instantiate some form of consciousness – albeit not identical to human consciousness. This essay posits how such trajectories could lead to the iterative development of “machine sentience” and addresses issues of what “machine consciousness” might mean for: 1) the ways that humans regard such machine entities as “beings” and/or “persons”, and 2) philosophical, ethical and socio-legal positions which might need to be adapted to guide and govern human treatment of, and interactions with such entities. Herein, I argue that neuroethics contributes crucial insights and viable tools to any meaningful approach to this topic (in synergy with extant discourse in “robo-ethics”). As the fields of neuro- and cognitive science, and computational engineering become increasingly convergent, so too must the philosophical and ethical approaches that can – and should – be employed to direct what convergent science may create. The speed and breadth of such technological development are such that neuroethical address and engagement of these issues and questions must be equivalently paced and iterative, so as to retain preparatory value.

This paper deals with the arrow of complexification of engineering. We claim that the complexification of engineering consists in (a) that shift throughout which engineering becomes a science; thus it ceases to be a (mere) praxis or profession; (b) becoming a science, engineering can be considered as one of the sciences of complexity. In reality, the complexification of engineering is the process by which engineering can be studied, achieved and understood in terms of knowledge, and not of goods and services any longer. Complex engineered systems and bio-inspired engineering are so far the two expressions of a complex engineering.

Two major goals in machine learning are the discovery and improvement of solutions to complex problems. In this paper, we argue that complexification, i.e. the incremental elaboration of solutions through adding new structure, achieves both these goals. We demonstrate the power of complexification through the NeuroEvolution of Augmenting Topologies (NEAT) method, which evolves increasingly complex neural network architectures. NEAT is applied to an open-ended coevolutionary robot duel domain where robot controllers compete head to head. Because the robot duel domain supports a wide range of strategies, and because coevolution benefits from an escalating arms race, it serves as a suitable testbed for studying complexification. When compared to the evolution of networks with fixed structure, complexifying evolution discovers significantly more sophisticated strategies. The results suggest that in order to discover and improve complex solutions, evolution, and search in general, should be allowed to complexify as well as optimize.