The design of DNN accelerators includes two key parts: HW resource configuration and mapping strategy. Intensive research has been conducted to optimize each of them independently. Unfortunately, optimizing for both together is extremely challenging due to the extremely large cross-coupled search space. To address this, in this paper, we propose a HW-Mapping co-optimization framework, an efficient encoding of the immense design space constructed by HW and Mapping, and a domain-aware genetic algorithm, named DiGamma, with specialized operators for improving search efficiency. We evaluate DiGamma with seven popular DNNs models with different properties. Our evaluations show DiGamma can achieve (geomean) 3.0x and 10.0x speedup, comparing to the best-performing baseline optimization algorithms, in edge and cloud settings.

Dataflow/mapping decides the compute and energy efficiency of DNN accelerators. Many mappers have been proposed to tackle the intra-layer map-space. However, mappers for inter-layer map-space (aka layer-fusion map-space), have been rarely discussed. In this work, we propose a mapper, DNNFuser, specifically focusing on this layer-fusion map-space. While existing SOTA DNN mapping explorations rely on search-based mappers, this is the first work, to the best of our knowledge, to propose a one-shot inference-based mapper. We leverage a famous language model GPT as our DNN architecture to learn layer-fusion optimization as a sequence modeling problem. Further, the trained DNNFuser can generalize its knowledge and infer new solutions for unseen conditions. Within one inference pass, DNNFuser can infer solutions with compatible performance to the ones found by a highly optimized search-based mapper while being 66x-127x faster.

Nature inspired computing draws on the principles of emergence, self-organization and complex systems. It aims to develop new techniques, algorithms and computational applications by getting ideas by observing how nature behaves to solve complex problem. Research on NIC has opened new branches such as evolutionary computation, neural networks, artificial immune systems. Robotics researchers, inspired by nature, have developed robotic salamander, water strider robot, mechanical cockroaches, self-configuring robots, and so on. The nature-inspired computing group creates and applies algorithms based on natural phenomena such as the human brain, evolution and swarms of insects.

Automated Machine Learning (AutoML) has been used successfully in settings where the learning task is assumed to be static. In many real-world scenarios, however, the data distribution will evolve over time, and it is yet to be shown whether AutoML techniques can effectively design online pipelines in dynamic environments. This study aims to automate pipeline design for online learning while continuously adapting to data drift. For this purpose, we design an adaptive Online Automated Machine Learning (OAML) system, searching the complete pipeline configuration space of online learners, including preprocessing algorithms and ensembling techniques. This system combines the inherent adaptation capabilities of online learners with the fast automated pipeline (re)optimization capabilities of AutoML. Focusing on optimization techniques that can adapt to evolving objectives, we evaluate asynchronous genetic programming and asynchronous successive halving to optimize these pipelines continually. We experiment on real and artificial data streams with varying types of concept drift to test the performance and adaptation capabilities of the proposed system. The results confirm the utility of OAML over popular online learning algorithms and underscore the benefits of continuous pipeline redesign in the presence of data drift.

Internet of Vehicles (IoV) over Vehicular Ad-hoc Networks (VANETS) is an emerging technology enabling the development of smart cities applications for safer, efficient, and pleasant travel. These applications have stringent requirements expressed in Service Level Agreements (SLAs). Considering vehicles limited computational and storage capabilities, applications requests are offloaded into an integrated edge-cloud computing system. Existing offloading solutions focus on optimizing applications Quality of Service (QoS) while respecting a single SLA constraint. They do not consider the impact of overlapped requests processing. Very few contemplate the varying speed of a vehicle. This paper proposes a novel Artificial Intelligence (AI) QoS-SLA-aware genetic algorithm (GA) for multi-request offloading in a heterogeneous edge-cloud computing system, considering the impact of overlapping requests processing and dynamic vehicle speed. The objective of the optimization algorithm is to improve the applications' Quality of Service (QoS) by minimizing the total execution time. The proposed algorithm integrates an adaptive penalty function to assimilate the SLAs constraints in terms of latency, processing time, deadline, CPU, and memory requirements. Numerical experiments and comparative analysis are achieved between our proposed QoS-SLA-aware GA, random, and GA baseline approaches. The results show that the proposed algorithm executes the requests 1.22 times faster on average compared to the random approach with 59.9% less SLA violations. While the GA baseline approach increases the performance of the requests by 1.14 times, it has 19.8% more SLA violations than our approach.

Hypervolume contribution is an important concept in evolutionary multi-objective optimization (EMO). It involves in hypervolume-based EMO algorithms and hypervolume subset selection algorithms. Its main drawback is that it is computationally expensive in high-dimensional spaces, which limits its applicability to many-objective optimization. Recently, an R2 indicator variant (i.e., $R_2^{\text{HVC}}$ indicator) is proposed to approximate the hypervolume contribution. The $R_2^{\text{HVC}}$ indicator uses line segments along a number of direction vectors for hypervolume contribution approximation. It has been shown that different direction vector sets lead to different approximation quality. In this paper, we propose \textit{Learning to Approximate (LtA)}, a direction vector set generation method for the $R_2^{\text{HVC}}$ indicator. The direction vector set is automatically learned from training data. The learned direction vector set can then be used in the $R_2^{\text{HVC}}$ indicator to improve its approximation quality. The usefulness of the proposed LtA method is examined by comparing it with other commonly-used direction vector set generation methods for the $R_2^{\text{HVC}}$ indicator. Experimental results suggest the superiority of LtA over the other methods for generating high quality direction vector sets.

In the evolutionary multi-objective optimization (EMO) field, the standard practice is to present the final population of an EMO algorithm as the output. However, it has been shown that the final population often includes solutions which are dominated by other solutions generated and discarded in previous generations. Recently, a new EMO framework has been proposed to solve this issue by storing all the non-dominated solutions generated during the evolution in an archive and selecting a subset of solutions from the archive as the output. The key component in this framework is the subset selection from the archive which usually stores a large number of candidate solutions. However, most studies on subset selection focus on small candidate solution sets for environmental selection. There is no benchmark test suite for large-scale subset selection. This paper aims to fill this research gap by proposing a benchmark test suite for subset selection from large candidate solution sets, and comparing some representative methods using the proposed test suite. The proposed test suite together with the benchmarking studies provides a baseline for researchers to understand, use, compare, and develop subset selection methods in the EMO field.

Consequently, any optimisation algorithm, including nonlinear optimisation heuristics, should be able to deal with such constraints by means of a constraint handling method. Such a method deals with infeasible solution (IS) candidates x R D by means of a suitable approach, involving concepts such as, e.g., ignoring or repairing them. In nonlinear optimisation heuristics inspired by nature, the infeasible components of a solution are generated by the mutation operator, which is expected to help explore regions of the search space outside the scope of the crossover operator and then converge towards solution candidates for which f is minimised or maximised. Intuitively, this search process is disrupted and thus lacks the ability to adapt itself to the properties of the objective function f when it generates many infeasible solutions during the course of the search. In this paper, we present an empirical investigation of the proportion of infeasible solutions generated for various variants and parameter settings of Differential Evolution. The algorithm variants under consideration are introduced in Section 2 while the adopted methods of dealing with generated infeasible solutions, as well as the experimental setup, are introduced in Section 3. The results are discussed in Section 4 and conclusions are drawn in Section 5. 2. Differential evolution Originally intended for a simple fitting problem [36, 31], Differential Evolution (DE) has soon become an established metaheuristic method for general-purpose real-valued optimisation, finding its place among other optimisation methods for real-world applications in engineering, robotics and other fields [35, 30, 41]. Besides the effectiveness of the DE optimisation framework, its success is attributed to the simplicity of its algorithmic structure. As can be seen from the pseudocode in Algorithm 1, it requires tuning only three parameters: the population size N (i.e., number of candidate solutions), the scaling factor F (i.e., a prefixed scalar multiplier in the range p0,2s involved in the mutation process) and the crossover rate C

Opponent modeling is the ability to use prior knowledge and observations in order to predict the behavior of an opponent. This survey presents a comprehensive overview of existing opponent modeling techniques for adversarial domains, many of which must address stochastic, continuous, or concurrent actions, and sparse, partially observable payoff structures. We discuss all the components of opponent modeling systems, including feature extraction, learning algorithms, and strategy abstractions. These discussions lead us to propose a new form of analysis for describing and predicting the evolution of game states over time. We then introduce a new framework that facilitates method comparison, analyze a representative selection of techniques using the proposed framework, and highlight common trends among recently proposed methods. Finally, we list several open problems and discuss future research directions inspired by AI research on opponent modeling and related research in other disciplines.

Self-driving cars, natural language recognition, and online recommendation engines are all possible thanks to Machine Learning. Now you can create your own genetic algorithms, nature-inspired swarms, Monte Carlo simulations, cellular automata, and clusters. Learn how to test your ML code and dive into even more advanced topics. If you are a beginner-to-intermediate programmer keen to understand machine learning, this book is for you. Get all eBook formats here for $24.95 (USD) Find indie bookstores in the U.S. Find indie bookstores around the world.