But these methods are unable to improve throughput (frames-per-second) on real-life hardware while simultaneously preserving robustness toadversarial perturbations.

As machine learning inferences increasingly move to edge devices, adapting to diverse computational capabilities, hardware, and memory constraints becomes more critical. Instead of relying on a pre-trained model fixed for all future inference queries across diverse edge devices, we argue that planning an inference pattern with a request-specific model tailored to the device's computational capacity, accuracy requirements, and time constraints is more cost-efficient and robust to diverse scenarios. To this end, we propose an accuracy-aware and workload-balanced inference system that integrates joint model quantization and inference partitioning. In this approach, the server dynamically responds to inference queries by sending a quantized model and adaptively sharing the inference workload with the device. Meanwhile, the device's computational power, channel capacity, and accuracy requirements are considered when deciding. Furthermore, we introduce a new optimization framework for the inference system, incorporating joint model quantization and partitioning. Our approach optimizes layer-wise quantization bit width and partition points to minimize time consumption and cost while accounting for varying accuracy requirements of tasks through an accuracy degradation metric in our optimization model. To our knowledge, this work represents the first exploration of optimizing quantization layer-wise bit-width in the inference serving system, by introducing theoretical measurement of accuracy degradation. Simulation results demonstrate a substantial reduction in overall time and power consumption, with computation payloads decreasing by over 80% and accuracy degradation kept below 1%.

The global energy landscape is undergoing a profound transformation, often referred to as the energy transition, driven by the urgent need to mitigate climate change, reduce greenhouse gas emissions, and ensure sustainable energy supplies. However, the undoubted complexity of new investments in renewables, as well as the phase out of high CO2-emission energy sources, hampers the pace of the energy transition and raises doubts as to whether new renewable energy sources are capable of solely meeting the climate target goals. This highlights the need to investigate alternative pathways to accelerate the energy transition, by identifying human activity domains with higher/excessive energy demands. Two notable examples where there is room for improvement, in the sense of reducing energy consumption and consequently CO2 emissions, are residential energy consumption and road transport. This dissertation investigates the development of novel Deep Learning techniques to create tools which solve limitations in these two key energy domains. Reduction of residential energy consumption can be achieved by empowering end-users with the user of Non-Intrusive Load Monitoring, whereas optimization of EV charging with Deep Reinforcement Learning can tackle road transport decarbonization.

--Background: As empirical software engineering evolves, more studies adopt data strategies--approaches that investigate digital artifacts such as models, source code, or system logs rather than relying on human subjects. Synthesizing results from such studies introduces new methodological challenges. Aims: This study assesses the effects of model quantization on correctness and resource efficiency in deep learning (DL) systems. Additionally, it explores the methodological implications of aggregating evidence from empirical studies that adopt data strategies. Method: We conducted a research synthesis of six primary studies that empirically evaluate model quantization. We applied the Structured Synthesis Method (SSM) to aggregate the findings, which combines qualitative and quantitative evidence through diagrammatic modeling. A total of 19 evidence models were extracted and aggregated. Results: The aggregated evidence indicates that model quantization weakly negatively affects correctness metrics while consistently improving resource efficiency metrics, including storage size, inference latency, and GPU energy consumption--a manageable trade-off for many DL deployment contexts. Evidence across quantization techniques remains fragmented, underscoring the need for more focused empirical studies per technique. Conclusions: Model quantization offers substantial efficiency benefits with minor trade-offs in correctness, making it a suitable optimization strategy for resource-constrained environments. This study also demonstrates the feasibility of using SSM to synthesize findings from data strategy-based research. Software engineering (SE) increasingly relies on data strategy studies [1] to understand and improve software development and deployment practices. Data strategies refer to "empirical studies that rely primarily on archival, generated or simulated data" [1], using a wide range of specific methods, including experiments and data mining studies. It is also partially funded by the Joan Or o pre-doctoral support program (BDNS 657443), co-funded by the European Union. Although these studies provide valuable information, they remain largely disconnected, with findings often limited to specific contexts and lacking broader theoretical integration. Therefore, the SE field struggles with few theories and needs more structured syntheses of existing research to guide future advancements.

Deep learning-based weed control systems often suffer from limited training data diversity and constrained on-board computation, impacting their real-world performance. To overcome these challenges, we propose a framework that leverages Stable Diffusion-based inpainting to augment training data progressively in 10% increments -- up to an additional 200%, thus enhancing both the volume and diversity of samples. Our approach is evaluated on two state-of-the-art object detection models, YOLO11(l) and RT-DETR(l), using the mAP50 metric to assess detection performance. We explore quantization strategies (FP16 and INT8) for both the generative inpainting and detection models to strike a balance between inference speed and accuracy. Deployment of the downstream models on the Jetson Orin Nano demonstrates the practical viability of our framework in resource-constrained environments, ultimately improving detection accuracy and computational efficiency in intelligent weed management systems.

Large language models (LLMs) show impressive performance in solving complex language tasks. However, its large number of parameters present significant challenges for the deployment and application of the model on edge devices. Compressing large language models to low bits can enable them to run on resource-constrained devices, often leading to performance degradation. To address this problem, we propose gradient-aware weight quantization (GWQ), the first quantization approach for low-bit weight quantization that leverages gradients to localize outliers, requiring only a minimal amount of calibration data for outlier detection. GWQ retains the weights corresponding to the top 1% outliers preferentially at FP16 precision, while the remaining non-outlier weights are stored in a low-bit format. GWQ found experimentally that utilizing the sensitive weights in the gradient localization model is more scientific compared to utilizing the sensitive weights in the Hessian matrix localization model. Compared to current quantization methods, GWQ can be applied to multiple language models and achieves lower PPL on the WikiText2 and C4 dataset. In the zero-shot task, GWQ quantized models have higher accuracy compared to other quantization methods. GWQ is also suitable for multimodal model quantization, and the quantized Qwen-VL family model is more accurate than other methods. Zero-shot target detection task dataset RefCOCO outperforms the current stat-of-the-arts method SPQR. GWQ achieves 1.2 times inference speedup in comparison to the original model, and effectively reduces the inference memory.

Understanding the meaning of infant cries is a significant challenge for young parents in caring for their newborns. The presence of background noise and the lack of labeled data present practical challenges in developing systems that can detect crying and analyze its underlying reasons. In this paper, we present a novel data-driven framework, "InfantCryNet," for accomplishing these tasks. To address the issue of data scarcity, we employ pre-trained audio models to incorporate prior knowledge into our model. We propose the use of statistical pooling and multi-head attention pooling techniques to extract features more effectively. Additionally, knowledge distillation and model quantization are applied to enhance model efficiency and reduce the model size, better supporting industrial deployment in mobile devices. Experiments on real-life datasets demonstrate the superior performance of the proposed framework, outperforming state-of-the-art baselines by 4.4% in classification accuracy. The model compression effectively reduces the model size by 7% without compromising performance and by up to 28% with only an 8% decrease in accuracy, offering practical insights for model selection and system design.

Deep learning-based models are at the forefront of most driver observation benchmarks due to their remarkable accuracies but are also associated with high computational costs. This is challenging, as resources are often limited in real-world driving scenarios. This paper introduces a lightweight framework for resource-efficient driver activity recognition. The framework enhances 3D MobileNet, a neural architecture optimized for speed in video classification, by incorporating knowledge distillation and model quantization to balance model accuracy and computational efficiency. Knowledge distillation helps maintain accuracy while reducing the model size by leveraging soft labels from a larger teacher model (I3D), instead of relying solely on original ground truth data. Model quantization significantly lowers memory and computation demands by using lower precision integers for model weights and activations. Extensive testing on a public dataset for in-vehicle monitoring during autonomous driving demonstrates that this new framework achieves a threefold reduction in model size and a 1.4-fold improvement in inference time, compared to an already optimized architecture. The code for this study is available at https://github.com/calvintanama/qd-driver-activity-reco.

Large language models (LLM), based on generative pre-trained transformers (GPT), such as ChatGPT show high efficiency in the analysis of complex texts. These days, we can observe the emerging of many new smaller open source LLMs, e.g. Llama, Falcon, GPT4All, GPT-J, etc. Open source LLMs can be fine-tuned for specific custom problems and deployed on custom servers, e.g. in cloud computing services such as AWS, GCP. LLMs have some new features as compared to conventional language models based on transformers. One of them is zero-shot and few-shot learning, which consists in good performance of the model when we show it only few training examples or even no examples at all, but only the instructions describing what should be done. Another important feature is the reasoning when a model can generate new patterns and conclusions which are based on an input prompt and facts known by the model and which were not included into it directly during a training process. So, the model can generate analytical texts with unexpected but useful chains of thoughts. One of the approaches of using LLMs is based on retrieval augmented generation (RAG), which uses the results from other services e.g.

Despite the proliferation of diverse hardware accelerators (e.g., NPU, TPU, DPU), deploying deep learning models on edge devices with fixed-point hardware is still challenging due to complex model quantization and conversion. Existing model quantization frameworks like Tensorflow QAT [1], TFLite PTQ [2], and Qualcomm AIMET [3] supports only a limited set of quantization schemes (e.g., only asymmetric per-tensor quantization in TF1.x QAT [4]). Accordingly, deep learning models cannot be easily quantized for diverse fixed-point hardwares, mainly due to slightly different quantization requirements. In this paper, we envision a new type of model quantization approach called MRQ (model re-quantization), which takes existing quantized models and quickly transforms the models to meet different quantization requirements (e.g., asymmetric -> symmetric, non-power-of-2 scale -> power-of-2 scale). Re-quantization is much simpler than quantizing from scratch because it avoids costly re-training and provides support for multiple quantization schemes simultaneously. To minimize re-quantization error, we developed a new set of re-quantization algorithms including weight correction and rounding error folding. We have demonstrated that MobileNetV2 QAT model [7] can be quickly re-quantized into two different quantization schemes (i.e., symmetric and symmetric+power-of-2 scale) with less than 0.64 units of accuracy loss. We believe our work is the first to leverage this concept of re-quantization for model quantization and models obtained from the re-quantization process have been successfully deployed on NNA in the Echo Show devices.