This research sheds light on the present and future landscape of Engineering Entrepreneurship Education (EEE) by exploring varied approaches and models adopted in Australian universities, evaluating program effectiveness, and offering recommendations for curriculum enhancement. While EEE programs have been in existence for over two decades, their efficacy remains underexplored. Using a multi-method approach encompassing self-reflection, scoping review, surveys, and interviews, this study addresses key research questions regarding the state, challenges, trends, and effectiveness of EEE. Findings reveal challenges like resource limitations and propose solutions such as experiential learning and industry partnerships. These insights underscore the importance of tailored EEE and inform teaching strategies and curriculum development, benefiting educators and policymakers worldwide.

The stochastic gradient descent (SGD) algorithm is the algorithm we use to train neural networks. However, it remains poorly understood how the SGD navigates the highly nonlinear and degenerate loss landscape of a neural network. In this work, we prove that the minibatch noise of SGD regularizes the solution towards a balanced solution whenever the loss function contains a rescaling symmetry. Because the difference between a simple diffusion process and SGD dynamics is the most significant when symmetries are present, our theory implies that the loss function symmetries constitute an essential probe of how SGD works. We then apply this result to derive the stationary distribution of stochastic gradient flow for a diagonal linear network with arbitrary depth and width. The stationary distribution exhibits complicated nonlinear phenomena such as phase transitions, broken ergodicity, and fluctuation inversion. These phenomena are shown to exist uniquely in deep networks, implying a fundamental difference between deep and shallow models.

For codes equipped with metrics such as Hamming metric, symbol pair metric or cover metric, the Johnson bound guarantees list-decodability of such codes. That is, the Johnson bound provides a lower bound on the list-decoding radius of a code in terms of its relative minimum distance $\delta$, list size $L$ and the alphabet size $q.$ For study of list-decodability of codes with insertion and deletion errors (we call such codes insdel codes), it is natural to ask the open problem whether there is also a Johnson-type bound. The problem was first investigated by Wachter-Zeh and the result was amended by Hayashi and Yasunaga where a lower bound on the list-decodability for insdel codes was derived. The main purpose of this paper is to move a step further towards solving the above open problem. In this work, we provide a new lower bound for the list-decodability of an insdel code. As a consequence, we show that unlike the Johnson bound for codes under other metrics that is tight, the bound on list-decodability of insdel codes given by Hayashi and Yasunaga is not tight. Our main idea is to show that if an insdel code with a given Levenshtein distance $d$ is not list-decodable with list size $L$, then the list decoding radius is lower bounded by a bound involving $L$ and $d$. In other words, if the list decoding radius is less than this lower bound, the code must be list-decodable with list size $L$. At the end of the paper we use such bound to provide an insdel-list-decodability bound for various well-known codes, which has not been extensively studied before.

Function-as-a-Service (FaaS) introduces a lightweight, function-based cloud execution model that finds its relevance in applications like IoT-edge data processing and anomaly detection. While CSP offer a near-infinite function elasticity, these applications often experience fluctuating workloads and stricter performance constraints. A typical CSP strategy is to empirically determine and adjust desired function instances, "autoscaling", based on monitoring-based thresholds such as CPU or memory, to cope with demand and performance. However, threshold configuration either requires expert knowledge, historical data or a complete view of environment, making autoscaling a performance bottleneck lacking an adaptable solution.RL algorithms are proven to be beneficial in analysing complex cloud environments and result in an adaptable policy that maximizes the expected objectives. Most realistic cloud environments usually involve operational interference and have limited visibility, making them partially observable. A general solution to tackle observability in highly dynamic settings is to integrate Recurrent units with model-free RL algorithms and model a decision process as a POMDP. Therefore, in this paper, we investigate a model-free Recurrent RL agent for function autoscaling and compare it against the model-free Proximal Policy Optimisation (PPO) algorithm. We explore the integration of a LSTM network with the state-of-the-art PPO algorithm to find that under our experimental and evaluation settings, recurrent policies were able to capture the environment parameters and show promising results for function autoscaling. We further compare a PPO-based autoscaling agent with commercially used threshold-based function autoscaling and posit that a LSTM-based autoscaling agent is able to improve throughput by 18%, function execution by 13% and account for 8.4% more function instances.

CNNs and Transformers have their own advantages and both have been widely used for dense prediction in multi-task learning (MTL). Most of the current studies on MTL solely rely on CNN or Transformer. In this work, we present a novel MTL model by combining both merits of deformable CNN and query-based Transformer with shared gating for multi-task learning of dense prediction. This combination may offer a simple and efficient solution owing to its powerful and flexible task-specific learning and advantages of lower cost, less complexity and smaller parameters than the traditional MTL methods. We introduce deformable mixer Transformer with gating (DeMTG), a simple and effective encoder-decoder architecture up-to-date that incorporates the convolution and attention mechanism in a unified network for MTL. It is exquisitely designed to use advantages of each block, and provide deformable and comprehensive features for all tasks from local and global perspective. First, the deformable mixer encoder contains two types of operators: the channel-aware mixing operator leveraged to allow communication among different channels, and the spatial-aware deformable operator with deformable convolution applied to efficiently sample more informative spatial locations. Second, the task-aware gating transformer decoder is used to perform the task-specific predictions, in which task interaction block integrated with self-attention is applied to capture task interaction features, and the task query block integrated with gating attention is leveraged to select corresponding task-specific features. Further, the experiment results demonstrate that the proposed DeMTG uses fewer GFLOPs and significantly outperforms current Transformer-based and CNN-based competitive models on a variety of metrics on three dense prediction datasets. Our code and models are available at //github.com/yangyangxu0/DeMTG.

Parameter design is significant in ensuring a satisfactory holistic performance of power converters. Generally, circuit parameter design for power converters consists of two processes: analysis and deduction process and optimization process. The existing approaches for parameter design consist of two types: traditional approach and computer-aided optimization (CAO) approach. In the traditional approaches, heavy human-dependence is required. Even though the emerging CAO approaches automate the optimization process, they still require manual analysis and deduction process. To mitigate human-dependence for the sake of high accuracy and easy implementation, an artificial-intelligence-based design (AI-D) approach is proposed in this article for the parameter design of power converters. In the proposed AI-D approach, to achieve automation in the analysis and deduction process, simulation tools and batch-normalization neural network (BN-NN) are adopted to build data-driven models for the optimization objectives and design constraints. Besides, to achieve automation in the optimization process, genetic algorithm is used to search for optimal design results. The proposed AI-D approach is validated in the circuit parameter design of the synchronous buck converter in the 48 to 12 V accessory-load power supply system in electric vehicle. The design case of an efficiency-optimal synchronous buck converter with constraints in volume, voltage ripple, and current ripple is provided. In the end of this article, feasibility and accuracy of the proposed AI-D approach have been validated by hardware experiments.

AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature.

This work considers the question of how convenient access to copious data impacts our ability to learn causal effects and relations. In what ways is learning causality in the era of big data different from -- or the same as -- the traditional one? To answer this question, this survey provides a comprehensive and structured review of both traditional and frontier methods in learning causality and relations along with the connections between causality and machine learning. This work points out on a case-by-case basis how big data facilitates, complicates, or motivates each approach.

Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.

We present a monocular Simultaneous Localization and Mapping (SLAM) using high level object and plane landmarks, in addition to points. The resulting map is denser, more compact and meaningful compared to point only SLAM. We first propose a high order graphical model to jointly infer the 3D object and layout planes from single image considering occlusions and semantic constraints. The extracted cuboid object and layout planes are further optimized in a unified SLAM framework. Objects and planes can provide more semantic constraints such as Manhattan and object supporting relationships compared to points. Experiments on various public and collected datasets including ICL NUIM and TUM mono show that our algorithm can improve camera localization accuracy compared to state-of-the-art SLAM and also generate dense maps in many structured environments.

This research sheds light on the present and future landscape of Engineering Entrepreneurship Education (EEE) by exploring varied approaches and models adopted in Australian universities, evaluating program effectiveness, and offering recommendations for curriculum enhancement. While EEE programs have been in existence for over two decades, their efficacy remains underexplored. Using a multi-method approach encompassing self-reflection, scoping review, surveys, and interviews, this study addresses key research questions regarding the state, challenges, trends, and effectiveness of EEE. Findings reveal challenges like resource limitations and propose solutions such as experiential learning and industry partnerships. These insights underscore the importance of tailored EEE and inform teaching strategies and curriculum development, benefiting educators and policymakers worldwide.

The stochastic gradient descent (SGD) algorithm is the algorithm we use to train neural networks. However, it remains poorly understood how the SGD navigates the highly nonlinear and degenerate loss landscape of a neural network. In this work, we prove that the minibatch noise of SGD regularizes the solution towards a balanced solution whenever the loss function contains a rescaling symmetry. Because the difference between a simple diffusion process and SGD dynamics is the most significant when symmetries are present, our theory implies that the loss function symmetries constitute an essential probe of how SGD works. We then apply this result to derive the stationary distribution of stochastic gradient flow for a diagonal linear network with arbitrary depth and width. The stationary distribution exhibits complicated nonlinear phenomena such as phase transitions, broken ergodicity, and fluctuation inversion. These phenomena are shown to exist uniquely in deep networks, implying a fundamental difference between deep and shallow models.

For codes equipped with metrics such as Hamming metric, symbol pair metric or cover metric, the Johnson bound guarantees list-decodability of such codes. That is, the Johnson bound provides a lower bound on the list-decoding radius of a code in terms of its relative minimum distance $\delta$, list size $L$ and the alphabet size $q.$ For study of list-decodability of codes with insertion and deletion errors (we call such codes insdel codes), it is natural to ask the open problem whether there is also a Johnson-type bound. The problem was first investigated by Wachter-Zeh and the result was amended by Hayashi and Yasunaga where a lower bound on the list-decodability for insdel codes was derived. The main purpose of this paper is to move a step further towards solving the above open problem. In this work, we provide a new lower bound for the list-decodability of an insdel code. As a consequence, we show that unlike the Johnson bound for codes under other metrics that is tight, the bound on list-decodability of insdel codes given by Hayashi and Yasunaga is not tight. Our main idea is to show that if an insdel code with a given Levenshtein distance $d$ is not list-decodable with list size $L$, then the list decoding radius is lower bounded by a bound involving $L$ and $d$. In other words, if the list decoding radius is less than this lower bound, the code must be list-decodable with list size $L$. At the end of the paper we use such bound to provide an insdel-list-decodability bound for various well-known codes, which has not been extensively studied before.

Function-as-a-Service (FaaS) introduces a lightweight, function-based cloud execution model that finds its relevance in applications like IoT-edge data processing and anomaly detection. While CSP offer a near-infinite function elasticity, these applications often experience fluctuating workloads and stricter performance constraints. A typical CSP strategy is to empirically determine and adjust desired function instances, "autoscaling", based on monitoring-based thresholds such as CPU or memory, to cope with demand and performance. However, threshold configuration either requires expert knowledge, historical data or a complete view of environment, making autoscaling a performance bottleneck lacking an adaptable solution.RL algorithms are proven to be beneficial in analysing complex cloud environments and result in an adaptable policy that maximizes the expected objectives. Most realistic cloud environments usually involve operational interference and have limited visibility, making them partially observable. A general solution to tackle observability in highly dynamic settings is to integrate Recurrent units with model-free RL algorithms and model a decision process as a POMDP. Therefore, in this paper, we investigate a model-free Recurrent RL agent for function autoscaling and compare it against the model-free Proximal Policy Optimisation (PPO) algorithm. We explore the integration of a LSTM network with the state-of-the-art PPO algorithm to find that under our experimental and evaluation settings, recurrent policies were able to capture the environment parameters and show promising results for function autoscaling. We further compare a PPO-based autoscaling agent with commercially used threshold-based function autoscaling and posit that a LSTM-based autoscaling agent is able to improve throughput by 18%, function execution by 13% and account for 8.4% more function instances.

CNNs and Transformers have their own advantages and both have been widely used for dense prediction in multi-task learning (MTL). Most of the current studies on MTL solely rely on CNN or Transformer. In this work, we present a novel MTL model by combining both merits of deformable CNN and query-based Transformer with shared gating for multi-task learning of dense prediction. This combination may offer a simple and efficient solution owing to its powerful and flexible task-specific learning and advantages of lower cost, less complexity and smaller parameters than the traditional MTL methods. We introduce deformable mixer Transformer with gating (DeMTG), a simple and effective encoder-decoder architecture up-to-date that incorporates the convolution and attention mechanism in a unified network for MTL. It is exquisitely designed to use advantages of each block, and provide deformable and comprehensive features for all tasks from local and global perspective. First, the deformable mixer encoder contains two types of operators: the channel-aware mixing operator leveraged to allow communication among different channels, and the spatial-aware deformable operator with deformable convolution applied to efficiently sample more informative spatial locations. Second, the task-aware gating transformer decoder is used to perform the task-specific predictions, in which task interaction block integrated with self-attention is applied to capture task interaction features, and the task query block integrated with gating attention is leveraged to select corresponding task-specific features. Further, the experiment results demonstrate that the proposed DeMTG uses fewer GFLOPs and significantly outperforms current Transformer-based and CNN-based competitive models on a variety of metrics on three dense prediction datasets. Our code and models are available at //github.com/yangyangxu0/DeMTG.

Parameter design is significant in ensuring a satisfactory holistic performance of power converters. Generally, circuit parameter design for power converters consists of two processes: analysis and deduction process and optimization process. The existing approaches for parameter design consist of two types: traditional approach and computer-aided optimization (CAO) approach. In the traditional approaches, heavy human-dependence is required. Even though the emerging CAO approaches automate the optimization process, they still require manual analysis and deduction process. To mitigate human-dependence for the sake of high accuracy and easy implementation, an artificial-intelligence-based design (AI-D) approach is proposed in this article for the parameter design of power converters. In the proposed AI-D approach, to achieve automation in the analysis and deduction process, simulation tools and batch-normalization neural network (BN-NN) are adopted to build data-driven models for the optimization objectives and design constraints. Besides, to achieve automation in the optimization process, genetic algorithm is used to search for optimal design results. The proposed AI-D approach is validated in the circuit parameter design of the synchronous buck converter in the 48 to 12 V accessory-load power supply system in electric vehicle. The design case of an efficiency-optimal synchronous buck converter with constraints in volume, voltage ripple, and current ripple is provided. In the end of this article, feasibility and accuracy of the proposed AI-D approach have been validated by hardware experiments.

AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature.

This work considers the question of how convenient access to copious data impacts our ability to learn causal effects and relations. In what ways is learning causality in the era of big data different from -- or the same as -- the traditional one? To answer this question, this survey provides a comprehensive and structured review of both traditional and frontier methods in learning causality and relations along with the connections between causality and machine learning. This work points out on a case-by-case basis how big data facilitates, complicates, or motivates each approach.

Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.

We present a monocular Simultaneous Localization and Mapping (SLAM) using high level object and plane landmarks, in addition to points. The resulting map is denser, more compact and meaningful compared to point only SLAM. We first propose a high order graphical model to jointly infer the 3D object and layout planes from single image considering occlusions and semantic constraints. The extracted cuboid object and layout planes are further optimized in a unified SLAM framework. Objects and planes can provide more semantic constraints such as Manhattan and object supporting relationships compared to points. Experiments on various public and collected datasets including ICL NUIM and TUM mono show that our algorithm can improve camera localization accuracy compared to state-of-the-art SLAM and also generate dense maps in many structured environments.