Computational Intelligence (CI) is the study of adaptive mechanisms to enable or facilitate intelligence behavior in complex and uncertain environments. The main objective of CI is to realize a new approach for analyzing and creating flexible information processing of humans such as sensing, understanding, learning, recognizing, and thinking. It plays a major role in developing successful intelligent systems, including games and cognitive developmental systems. Some of the most successful AI systems are based on CI. In this view AI is a part of CI focused on problems related to higher cognitive functions, while the rest of the CI community works on problems related to perception and control, or lower cognitive functions.

This article was published as a part of the Data Science Blogathon. There are multiple ways that one can take to either minimize or maximize any function so that the optimal value can be found out. You can find several optimisation solutions on the internet but in the end, no one solution is the best for all. Everyone has its own advantage and disadvantages. The one that we are going to discuss here is the PSO or the Particle Swarm Optimization.

Collective behavior is widespread across the animal kingdom. To date, however, the developmental and mechanistic foundations of collective behavior have not been formally established. What learning mechanisms drive the development of collective behavior in newborn animals? Here, we used deep reinforcement learning and curiosity-driven learning -- two learning mechanisms deeply rooted in psychological and neuroscientific research -- to build newborn artificial agents that develop collective behavior. Like newborn animals, our agents learn collective behavior from raw sensory inputs in naturalistic environments. Our agents also learn collective behavior without external rewards, using only intrinsic motivation (curiosity) to drive learning. Specifically, when we raise our artificial agents in natural visual environments with groupmates, the agents spontaneously develop ego-motion, object recognition, and a preference for groupmates, rapidly learning all of the core skills required for collective behavior. This work bridges the divide between high-dimensional sensory inputs and collective action, resulting in a pixels-to-actions model of collective animal behavior. More generally, we show that two generic learning mechanisms -- deep reinforcement learning and curiosity-driven learning -- are sufficient to learn collective behavior from unsupervised natural experience.

Algorithmic design in neural architecture search (NAS) has received a lot of attention, aiming to improve performance and reduce computational cost. Despite the great advances made, few authors have proposed to tailor initialization techniques for NAS. However, literature shows that a good initial set of solutions facilitate finding the optima. Therefore, in this study, we propose a data-driven technique to initialize a population-based NAS algorithm. Particularly, we proposed a two-step methodology. First, we perform a calibrated clustering analysis of the search space, and second, we extract the centroids and use them to initialize a NAS algorithm. We benchmark our proposed approach against random and Latin hypercube sampling initialization using three population-based algorithms, namely a genetic algorithm, evolutionary algorithm, and aging evolution, on CIFAR-10. More specifically, we use NAS-Bench-101 to leverage the availability of NAS benchmarks. The results show that compared to random and Latin hypercube sampling, the proposed initialization technique enables achieving significant long-term improvements for two of the search baselines, and sometimes in various search scenarios (various training budgets). Moreover, we analyze the distributions of solutions obtained and find that that the population provided by the data-driven initialization technique enables retrieving local optima (maxima) of high fitness and similar configurations.

Learning optimal policies in sparse rewards settings is difficult as the learning agent has little to no feedback on the quality of its actions. In these situations, a good strategy is to focus on exploration, hopefully leading to the discovery of a reward signal to improve on. A learning algorithm capable of dealing with this kind of settings has to be able to (1) explore possible agent behaviors and (2) exploit any possible discovered reward. Efficient exploration algorithms have been proposed that require to define a behavior space, that associates to an agent its resulting behavior in a space that is known to be worth exploring. The need to define this space is a limitation of these algorithms. In this work, we introduce STAX, an algorithm designed to learn a behavior space on-the-fly and to explore it while efficiently optimizing any reward discovered. It does so by separating the exploration and learning of the behavior space from the exploitation of the reward through an alternating two-steps process. In the first step, STAX builds a repertoire of diverse policies while learning a low-dimensional representation of the high-dimensional observations generated during the policies evaluation. In the exploitation step, emitters are used to optimize the performance of the discovered rewarding solutions. Experiments conducted on three different sparse reward environments show that STAX performs comparably to existing baselines while requiring much less prior information about the task as it autonomously builds the behavior space.

Federated learning is a method that stores only learnt models on a server in order to protect data privacy. This approach does not collect data on the server but instead collects data from scattered clients directly. Due to the fact that federated learning clients frequently have limited transmission bandwidth, communication between servers and clients should be streamlined to maximize performance. As a result, researchers have created the FedPSO algorithm, which combines the particle swarm optimization technique with federated learning to boost network communication performance. We will attempt to cover certain aspects of this system and comprehend the proposed system in this post.

We formulate seven fundamental principles of evolution that appear to be necessary and sufficient to render a universe observable and show that they entail the major features of biological evolution, including replication and natural selection. These principles also follow naturally from the theory of learning. We formulate the theory of evolution using the mathematical framework of neural networks, which provides for detailed analysis of evolutionary phenomena. To demonstrate the potential of the proposed theoretical framework, we derive a generalized version of the Central Dogma of molecular biology by analyzing the flow of information during learning (back-propagation) and predicting (forward-propagation) the environment by evolving organisms. The more complex evolutionary phenomena, such as major transitions in evolution, in particular, the origin of life, have to be analyzed in the thermodynamic limit, which is described in detail in the accompanying paper. Significance statement Modern evolutionary theory gives a detailed quantitative description of microevolutionary processes that occur within evolving populations of organisms, but evolutionary transitions and emergence of multiple levels of complexity remain poorly understood. Here we establish correspondence between the key features of evolution, renormalizability of physical theories and learning dynamics, to outline a theory of evolution that strives to incorporate all evolutionary processes within a unified mathematical framework of the theory of learning. Under this theory, for example, natural selection readily arises from the learning dynamics, and in sufficiently complex systems, the same learning phenomena occur on multiple levels or on different scales, similar to the case of renormalizable physical theories.

Some people have updated other people's views and understanding of life with the new idea they presented. Darwin is undoubtedly one of these people. Darwin's difference from other biologists and researchers is that he explains the evolutionary process in an algorithmic way and bases it on the laws of nature. Darwin's dangerous idea began in biology but has spread from engineering to sociology. There is greatness in this idea to be able to conceive of infinite beauty and complexity.

The dinosaur is a chimera. Some parts of this complex assemblage are the result of biological evolution. But others are products of human ingenuity, constructed by artists, scientists, and technicians in a laborious process that stretches from the dig site to the naturalist's study and the museum's preparation lab. The mounted skeletons that have become such a staple of natural history museums most closely resemble mixed media sculptures, having been cobbled together from a large number of disparate elements that include plaster, steel, and paint, in addition to fossilized bone. When standing before one of these towering creatures, such as the T. rex skeleton named Sue in Chicago's Field Museum of Natural History, it is surprisingly difficult to distinguish which features are ancient and which ones are modern, where prehistory ends and imagination begins. If dinosaurs in museums are chimeras, their prehistoric antecedents are unobservable entities. In this respect, dinosaurs resemble subatomic particles like electrons, neutrons, and positrons. Both are inaccessible to direct observation, but for different reasons.

The image synthesis technique is relatively well established which can generate facial images that are indistinguishable even by human beings. However, all of these approaches uses gradients to condition the output, resulting in the outputting the same image with the same input. Also, they can only generate images with basic expression or mimic an expression instead of generating compound expression. In real life, however, human expressions are of great diversity and complexity. In this paper, we propose an evolutionary algorithm (EA) assisted GAN, named EvoGAN, to generate various compound expressions with any accurate target compound expression. EvoGAN uses an EA to search target results in the data distribution learned by GAN. Specifically, we use the Facial Action Coding System (FACS) as the encoding of an EA and use a pre-trained GAN to generate human facial images, and then use a pre-trained classifier to recognize the expression composition of the synthesized images as the fitness function to guide the search of the EA. Combined random searching algorithm, various images with the target expression can be easily sythesized. Quantitative and Qualitative results are presented on several compound expressions, and the experimental results demonstrate the feasibility and the potential of EvoGAN.