Algorithms in fields like image manipulation, sound and signal processing, and statistics frequently employ tight loops. These loops are computationally intensive and CPU-bound, making their performance highly dependent on efficient utilization of the CPU pipeline and memory bus. Recent years have seen CPU pipelines becoming more and more complicated, with features such as branch prediction and speculative execution. At the same time, clock speeds have stopped their prior exponential growth rate due to heat dissipation issues, and multiple cores have become prevalent. These developments have made it more difficult for developers to reason about how their code executes on the CPU, which in turn makes it difficult to write performant code. An automated method to take code and optimize it for most efficient execution would, therefore, be desirable. The Polyhedral Model allows the generation of alternative transformations for a loop nest that are semantically equivalent to the original. The transformations vary the degree of loop tiling, loop fusion, loop unrolling, parallelism, and vectorization. However, selecting the transformation that would most efficiently utilize the architecture remains challenging. Previous work utilizes regression models to select a transformation, using as features hardware performance counter values collected during a sample run of the program being optimized. Due to inaccuracies in the resulting regression model, the transformation selected by the model as the best transformation often yields unsatisfactory performance. As a result, previous work resorts to using a five-shot technique, which entails running the top five transformations suggested by the model and selecting the best one based on their actual runtime. However, for long-running benchmarks, five runs may be take an excessive amount of time. I present a variation on the previous approach which does not need to resort to the five-shot selection process to achieve performance comparable to the best five-shot results reported in previous work. With the transformations in the search space ranked in reverse runtime order, the transformation selected by my classifier is, on average, in the 86th percentile. There are several key contributing factors to the performance improvements attained by my method: formulating the problem as a classification problem rather than a regression problem, using static features in addition to dynamic performance counter features, performing feature selection, and using ensemble methods to boost the performance of the classifier. Decision trees are constructed from pairs of features (performance counters and structural features than can be determined statically from the source code). The trees are then evaluated according to the number of benchmarks for which they select a transformation that performs better than two baseline variants, the original program and the expected runtime if a randomly selected transformation were applied. The top 20 trees vote to select a final transformation.

Thailand is called the kitchen of the world; the country produces food and beverage products and exports around the globe. According to previous studies, there is not enough data on food waste in Thailand and worldwide. This study aims to analyse the characteristic of the loop of learning in assisting the process of organizational change and explain how it can support sustainable change in Food Waste Management. Even though a loop of learning is used frequently to develop changes in organizations, the relationship between organisational learning methods and organisational change is still not yet identified.  The qualitative method, particularly a case study, was used to accomplish the aim. The case study focuses on how production companies develop their organisational change toward sustainable Food Waste Management in Thailand by aligning the management's thinking level with a loop of learning. The data collection method is a semi-structured interview with 12 managers of different food and beverage manufacturing companies. The results show that current actions are 1) following the existing regulation and finding solutions for challenges, 2) developing better methods and re-using waste, and 3) setting new strategies to achieve sustainable Food Waste Management. Thus, those actions have the quality of single, double and triple-loop learning.  Furthermore, the research findings indicate that changing norms with environmental concerns can influence other factors, such as laws and stakeholder expectations. The organizational change process must involve continually thinking in the loop of learning from an individual and organisational perspective. These authors conclude that the nature of loop learning is a process that individuals and organizations can use to identify and reclaim problems; this process assists organization to realise the need for changes and continue developing solutions for those matters. The outcomes of continuous thinking will present changes in action which reach organisational change.

京都大学 / 新制・課程博士 / 博士(情報学) / 甲第24856号 / 情博第838号 / 新制||情||140(附属図書館) / 京都大学大学院情報学研究科知能情報学専攻 / (主査)教授 鹿島, 久嗣, 教授 河原, 達也, 教授 森本, 淳 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

Human-AI interaction can improve overall performance, exceeding the performance that either humans or AI could achieve separately, thus producing a whole greater than the sum of the parts. Visual analytics enables collaboration between humans and AI through interactive visual interfaces. Semantic interaction is a design methodology to enhance visual analytics systems for sensemaking tasks. It is widely applied for sensemaking in high-stakes domains such as intelligence analysis and academic research. However, existing semantic interaction systems support collaboration between humans and traditional machine learning models only; they do not apply state-of-the-art deep learning techniques. The contribution of this work is the effective integration of deep neural networks into visual analytics systems with semantic interaction. More specifically, I explore how to redesign the semantic interaction pipeline to enable collaboration between human and deep learning models for sensemaking tasks. First, I validate that semantic interaction systems with pre-trained deep learning better support sensemaking than existing semantic interaction systems with traditional machine learning. Second, I integrate interactive deep learning into the semantic interaction pipeline to enhance inference ability in capturing analysts' precise intents, thereby promoting sensemaking. Third, I add semantic explanation into the pipeline to interpret the interactively steered deep learning model. With a clear understanding of DL, analysts can make better decisions. Finally, I present a neural design of the semantic interaction pipeline to further boost collaboration between humans and deep learning for sensemaking. / Doctor of Philosophy / Human AI interaction can harness the separate strengths of human and machine intelligence to accomplish tasks neither can solve alone. Analysts are good at making high-level hypotheses and reasoning from their domain knowledge. AI models are better at data computation based on low-level input features. Successful human-AI interactions can perform real-world, high-stakes tasks, such as issuing medical diagnoses, making credit assessments, and determining cases of discrimination. Semantic interaction is a visual methodology providing intuitive communications between analysts and traditional machine learning models. It is commonly utilized to enhance visual analytics systems for sensemaking tasks, such as intelligence analysis and scientific research. The contribution of this work is to explore how to use semantic interaction to achieve collaboration between humans and state-of-the-art deep learning models for complex sensemaking tasks. To do this, I first evaluate the straightforward solution of integrating the pretrained deep learning model into the traditional semantic interaction pipeline. Results show that the deep learning representation matches human cognition better than hand engineering features via semantic interaction. Next, I look at methods for supporting semantic interaction systems with interactive and interpretable deep learning. The new pipeline provides effective communication between human and deep learning models. Interactive deep learning enables the system to better capture users' intents. Interpretable deep learning lets users have a clear understanding of models. Finally, I improve the pipeline to better support collaboration using a neural design. I hope this work can contribute to future designs for the human-in-the-loop analysis with deep learning and visual analytics techniques.