Towards Self-organized Control: Using Neural Cellular Automata to Robustly Control a Cart-pole Agent

Neural cellular automata (Neural CA) are a recent framework used to model biological phenomena emerging from multicellular organisms. In these systems, artificial neural networks are used as update rules for cellular automata. Neural CA are end-to-end differentiable systems where the parameters of the neural network can be learned to achieve a particular task. In this work, we used neural CA to control a cart-pole agent. The observations of the environment are transmitted in input cells while the values of output cells are used as a readout of the system. We trained the model using deep-Q learning where the states of the output cells were used as the Q-value estimates to be optimized. We found that the computing abilities of the cellular automata were maintained over several hundreds of thousands of iterations, producing an emergent stable behavior in the environment it controls for thousands of steps. Moreover, the system demonstrated life-like phenomena such as a developmental phase, regeneration after damage, stability despite a noisy environment, and robustness to unseen disruption such as input deletion.

Meta-learning prediction of physical and chemical properties of magnetized water and fertilizer based on LSTM

Background Due to the high cost of data collection for magnetization detection of media, the sample size is limited, it is not suitable to use deep learning method to predict its change trend. The prediction of physical and chemical properties of magnetized water and fertilizer (PCPMWF) by meta-learning can help to explore the effects of magnetized water and fertilizer irrigation on crops. Method In this article, we propose a meta-learning optimization model based on the meta-learner LSTM in the field of regression prediction of PCPMWF. In meta-learning, LSTM is used to replace MAML’s gradient descent optimizer for regression tasks, enables the meta-learner to learn the update rules of the LSTM, and apply it to update the parameters of the model. The proposed method is compared with the experimental results of MAML and LSTM to verify the feasibility and correctness. Results The average absolute percentage error of the meta-learning optimization model of meta-learner LSTM is reduced by 0.37% compared with the MAML model, and by 4.16% compared with the LSTM model. The loss value of the meta-learning optimization model in the iterative process drops the fastest and steadily compared to the MAML model and the LSTM model. In cross-domain experiments, the average accuracy of the meta-learning optimized model can still reach 0.833. Conclusions In the case of few sample, the proposed model is superior to the traditional LSTM model and the basic MAML model. And in the training of cross-domain datasets, this model performs best.

Dynamic Complexity of Parity Exists Queries

Given a graph whose nodes may be coloured red, the parity of the number of red nodes can easily be maintained with first-order update rules in the dynamic complexity framework DynFO of Patnaik and Immerman. Can this be generalised to other or even all queries that are definable in first-order logic extended by parity quantifiers? We consider the query that asks whether the number of nodes that have an edge to a red node is odd. Already this simple query of quantifier structure parity-exists is a major roadblock for dynamically capturing extensions of first-order logic. We show that this query cannot be maintained with quantifier-free first-order update rules, and that variants induce a hierarchy for such update rules with respect to the arity of the maintained auxiliary relations. Towards maintaining the query with full first-order update rules, it is shown that degree-restricted variants can be maintained.

Research on Optimal Scheduling in Cloud Computing

Aiming at the problem of unbalanced load and slow convergence speed of task scheduling based on ant colony algorithm, an improved task scheduling optimization algorithm is proposed. The pheromone update rules of ant colony algorithm are optimized by giving weight to speed up the solution speed. The comprehensive performance of the algorithm is optimized by dynamically updating the volatilization coefficient, and in the updating process of local pheromone. The load weight coefficient of virtual machine is introduced to ensure the load balance of virtual machine. The experimental results show that the task scheduling strategy of the improved algorithm can not only ensure the reasonable allocation of tasks, but also improve the convergence speed and shorten the total execution time.

Coordination and Equilibrium Selection in Games: The Role of Local Effects

We study the role of local effects and finite size effects in reaching coordination and in equilibrium selection in two-player coordination games. We investigate three update rules – the replicator dynamics (RD), the best response (BR), and the unconditional imitation (UI). For the pure coordination game with two equivalent strategies we find a transition from a disordered state to coordination for a critical value of connectivity. The transition is system-size-independent for the BR and RD update rules. For the IU it is system-size-dependent, but coordination can always be reached below the connectivity of a complete graph. We also consider the general coordination game which covers a range of games, such as the stag hunt. For these games there is a payoff-dominant strategy and a risk-dominant strategy with associated states of equilibrium coordination. We analyse equilibrium selection analytically and numerically. For the RD and BR update rules mean-field predictions agree with simulations and the risk-dominant strategy is evolutionary favoured independently of local effects. When players use the unconditional imitation, however, we observe coordination in the payoff-dominant strategy. Surprisingly, the selection of pay-off dominant equilibrium only occurs below a critical value of the network connectivity and disappears in complete graphs. As we show, it is a combination of local effects and update rule that allows for coordination on the payoff-dominant strategy.

Evolutionary algorithms for designing reversible cellular automata

Reversible Cellular Automata (RCA) are a particular kind of shift-invariant transformations characterized by dynamics composed only of disjoint cycles. They have many applications in the simulation of physical systems, cryptography, and reversible computing. In this work, we formulate the search of a specific class of RCA – namely, those whose local update rules are defined by conserved landscapes – as an optimization problem to be tackled with Genetic Algorithms (GA) and Genetic Programming (GP). In particular, our experimental investigation revolves around three different research questions, which we address through a single-objective, a multi-objective, and a lexicographic approach. In the single-objective approach, we observe that GP can already find an optimal solution in the initial population. This indicates that evolutionary algorithms are not needed when evolving only the reversibility of such CA, and a more efficient method is to generate at random syntactic trees that define the local update rule. On the other hand, GA and GP proved to be quite effective in the multi-objective and lexicographic approach to (1) discover a trade-off between the reversibility and the Hamming weight of conserved landscape rules, and (2) observe that conserved landscape CA cannot be used in symmetric cryptography because their Hamming weight (and thus their nonlinearity) is too low.

Minimum complexity drives regulatory logic in Boolean models of living systems

The properties of random Boolean networks as models of gene regulation have been investigated extensively by the statistical physics community. In the past two decades, there has been a dramatic increase in the reconstruction and analysis of Boolean models of biological networks. In such models, neither network topology nor Boolean functions (or logical update rules) should be expected to be random. In this contribution, we focus on biologically meaningful types of Boolean functions, and perform a systematic study of their preponderance in gene regulatory networks. By applying the k[P] classification based on number of inputs k and bias P of functions, we find that most Boolean functions astonishingly have odd bias in a reference biological dataset of 2687 functions compiled from published models. Subsequently, we are able to explain this observation along with the enrichment of read-once functions (RoFs) and its subset, nested canalyzing functions (NCFs), in the reference dataset in terms of two complexity measures: Boolean complexity based on string lengths in formal logic which is yet unexplored in the biological context, and the average sensitivity. Minimizing the Boolean complexity naturally sifts out a subset of odd-biased Boolean functions which happen to be the RoFs. Finally, we provide an analytical proof that NCFs minimize not only the Boolean complexity, but also the average sensitivity in their k[P] set.

Meta-learning Prediction of Physical and Chemical Properties of Magnetized Water and Fertilizer Based on LSTM

BackgroundDue to the high cost of data collection and labeling for magnetization detection of medium, the sample size is limited, it is not suitable to use deep learning method to predict its change trend. The prediction of physical and chemical properties of magnetized water and fertilizer(PCPMWF) by meta-learning can help to explore the effects of magnetized water and fertilizer irrigation on crops. MethodIn this article, we propose a meta-learning optimization model based on the meta-learner LSTM in the field of regression prediction of PCPMWF. In meta-learning, LSTM is used to replace MAML's gradient descent optimizer for regression tasks, enables the meta-learner to learn the update rules of the LSTM, and apply it to update the parameters of the model. The proposed method is compared with the experimental results of MAML and LSTM to verify the feasibility and correctness.ResultsThe average absolute percentage error of the meta-learning optimization model of meta-learner LSTM is reduced by 0.37% compared with the MAML model, and by 4.16% compared with the LSTM model.ConclusionsIn the case of few sample, the proposed model is superior to the traditional LSTM model and the basic MAML model.

Topology Optimization With Locally Evaluable Complement Space Connectivity

Enforcing connectivity of parts or their complement space during automated design is essential for various manufacturing and functional considerations such as removing powder, wiring internal components, and flowing internal coolant. The global nature of connectivity makes it difficult to incorporate into generative design methods that rely on local decision making, e.g., topology optimization (TO) algorithms whose update rules depend on the sensitivity of objective functions or constraints to locally change the design. Connectivity is commonly corrected for in a post-processing step, which may result in suboptimal designs. We propose a recasting of the connectivity constraint as a locally differentiable violation measure, defined as a “virtual” compliance, modeled after physical (e.g., thermal or structural) compliance. Such measures can be used within TO alongside other objective functions and constraints, using a weighted penalty scheme to navigate tradeoffs. By carefully specifying the boundary conditions of the virtual compliance problem, the designer can enforce connectivity between arbitrary regions of the part’s complement space while satisfying a primary objective function in the TO loop. We demonstrate the effectiveness of our approach using both 2D and 3D examples, show its flexibility to consider multiple virtual domains, and confirm the benefits of considering connectivity in the design loop rather than enforcing it through post-processing.