AIREPAIR: A Repair Platform for Neural Networks Song, Xidan; Sun, Youcheng; Mustafa, Mustafa A. ...
2023 IEEE/ACM 45th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)
Conference Proceeding
Odprti dostop
We present AIREPAIR, a platform for repairing neural networks. It features the integration of existing network repair tools. Based on AIREPAIR, one can run different repair methods on the same model, ...thus enabling the fair compari-son of different repair techniques. In this paper, we evaluate AIREPAIR with five recent repair methods on popular deep-learning datasets and models. Our evaluation confirms the utility of AIREPAIR, by comparing and analyzing the results from different repair techniques. A demonstration is available at https://youtu.be/UkKw5neeWhw
While Deep Neural Networks (DNNs) push the state-of-the-art in many machine learning applications, they often require millions of expensive floating-point operations for each input classification. ...This computation overhead limits the applicability of DNNs to low-power, embedded platforms and incurs high cost in data centers. This motivates recent interests in designing low-power, low-latency DNNs based on fixed-point, ternary, or even binary data precision. While recent works in this area offer promising results, they often lead to large accuracy drops when compared to the floating-point networks. We propose a novel approach to map floating-point based DNNs to 8-bit dynamic fixed-point networks with integer power-of-two weights with no change in network architecture. Our dynamic fixed-point DNNs allow different radix points between layers. During inference, power-of-two weights allow multiplications to be replaced with arithmetic shifts, while the 8-bit fixed-point representation simplifies both the buffer and adder design. In addition, we propose a hardware accelerator design to achieve low-power, low-latency inference with insignificant degradation in accuracy. Using our custom accelerator design with the CIFAR-10 and ImageNet datasets, we show that our method achieves significant power and energy savings while increasing the classification accuracy.
Machine learning develops rapidly, which has made many theoretical breakthroughs and is widely applied in various fields. Optimization, as an important part of machine learning, has attracted much ...attention of researchers. With the exponential growth of data amount and the increase of model complexity, optimization methods in machine learning face more and more challenges. A lot of work on solving optimization problems or improving optimization methods in machine learning has been proposed successively. The systematic retrospect and summary of the optimization methods from the perspective of machine learning are of great significance, which can offer guidance for both developments of optimization and machine learning research. In this article, we first describe the optimization problems in machine learning. Then, we introduce the principles and progresses of commonly used optimization methods. Finally, we explore and give some challenges and open problems for the optimization in machine learning.
Learning to Prompt for Continual Learning Wang, Zifeng; Zhang, Zizhao; Lee, Chen-Yu ...
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),
2022-June
Conference Proceeding
Odprti dostop
The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge. Typical methods ...rely on a rehearsal buffer or known task identity at test time to retrieve learned knowl-edge and address forgetting, while this work presents a new paradigm for continual learning that aims to train a more succinct memory system without accessing task identity at test time. Our method learns to dynamically prompt (L2P) a pre-trained model to learn tasks sequen-tially under different task transitions. In our proposed framework, prompts are small learnable parameters, which are maintained in a memory space. The objective is to optimize prompts to instruct the model prediction and ex-plicitly manage task-invariant and task-specific knowledge while maintaining model plasticity. We conduct comprehen-sive experiments under popular image classification bench-marks with different challenging continual learning set-tings, where L2P consistently outperforms prior state-of-the-art methods. Surprisingly, L2P achieves competitive results against rehearsal-based methods even without a re-hearsal buffer and is directly applicable to challenging task-agnostic continual learning. Source code is available at https://github.com/google-research/12p.
Phishing is an attack targeting to imitate the official websites of corporations such as banks, e-commerce, financial institutions, and governmental institutions. Phishing websites aim to access and ...retrieve users’ important information such as personal identification, social security number, password, e-mail, credit card, and other account information. Several anti-phishing techniques have been developed to cope with the increasing number of phishing attacks so far. Machine learning and particularly, deep learning algorithms are nowadays the most crucial techniques used to detect and prevent phishing attacks because of their strong learning abilities on massive datasets and their state-of-the-art results in many classification problems. Previously, two types of feature extraction techniques i.e., character embedding-based and manual natural language processing (NLP) feature extraction were used in isolation. However, researchers did not consolidate these features and therefore, the performance was not remarkable. Unlike previous works, our study presented an approach that utilizes both feature extraction techniques. We discussed how to combine these feature extraction techniques to fully utilize from the available data. This paper proposes hybrid deep learning models based on long short-term memory and deep neural network algorithms for detecting phishing uniform resource locator and evaluates the performance of the models on phishing datasets. The proposed hybrid deep learning models utilize both character embedding and NLP features, thereby simultaneously exploiting deep connections between characters and revealing NLP-based high-level connections. Experimental results showed that the proposed models achieve superior performance than the other phishing detection models in terms of accuracy metric.
Computer applications have considerably shifted from single data processing to machine learning in recent years due to the accessibility and availability of massive volumes of data obtained through ...the internet and various sources. Machine learning is automating human assistance by training an algorithm on relevant data. Supervised, Unsupervised, and Reinforcement Learning are the three fundamental categories of machine learning techniques. In this paper, we have discussed the different learning styles used in the field of Computer vision, Deep Learning, Neural networks, and machine learning. Some of the most recent applications of machine learning in computer vision include object identification, object classification, and extracting usable information from images, graphic documents, and videos. Some machine learning techniques frequently include zero-shot learning, active learning, contrastive learning, self-supervised learning, life-long learning, semi-supervised learning, ensemble learning, sequential learning, and multi-view learning used in computer vision until now. There is a lack of systematic reviews about all learning styles. This paper presents literature analysis of how different machine learning styles evolved in the field of Artificial Intelligence (AI) for computer vision. This research examines and evaluates machine learning applications in computer vision and future forecasting. This paper will be helpful for researchers working with learning styles as it gives a deep insight into future directions.
Keeping track of and managing Self-Admitted Technical Debts (SATDs) are important to maintaining a healthy software project. This requires much time and effort from human experts to identify the ...SATDs manually. The current automated solutions do not have satisfactory precision and recall in identifying SATDs to fully automate the process. To solve the above problems, we propose a two-step framework called Jitterbug for identifying SATDs. Jitterbug first identifies the "easy to find" SATDs automatically with close to 100 percent precision using a novel pattern recognition technique. Subsequently, machine learning techniques are applied to assist human experts in manually identifying the remaining "hard to find" SATDs with reduced human effort. Our simulation studies on ten software projects show that Jitterbug can identify SATDs more efficiently (with less human effort) than the prior state-of-the-art methods.
Abstract
Objective
To conduct a systematic scoping review of explainable artificial intelligence (XAI) models that use real-world electronic health record data, categorize these techniques according ...to different biomedical applications, identify gaps of current studies, and suggest future research directions.
Materials and Methods
We searched MEDLINE, IEEE Xplore, and the Association for Computing Machinery (ACM) Digital Library to identify relevant papers published between January 1, 2009 and May 1, 2019. We summarized these studies based on the year of publication, prediction tasks, machine learning algorithm, dataset(s) used to build the models, the scope, category, and evaluation of the XAI methods. We further assessed the reproducibility of the studies in terms of the availability of data and code and discussed open issues and challenges.
Results
Forty-two articles were included in this review. We reported the research trend and most-studied diseases. We grouped XAI methods into 5 categories: knowledge distillation and rule extraction (N = 13), intrinsically interpretable models (N = 9), data dimensionality reduction (N = 8), attention mechanism (N = 7), and feature interaction and importance (N = 5).
Discussion
XAI evaluation is an open issue that requires a deeper focus in the case of medical applications. We also discuss the importance of reproducibility of research work in this field, as well as the challenges and opportunities of XAI from 2 medical professionals’ point of view.
Conclusion
Based on our review, we found that XAI evaluation in medicine has not been adequately and formally practiced. Reproducibility remains a critical concern. Ample opportunities exist to advance XAI research in medicine.
Anticipating the rise in Artificial Intelligence’s ability to produce original works of literature, this study suggests that literariness, or that which constitutes a text as literary, is ...understudied in relation to text generation. From a computational perspective, literature is particularly challenging because it typically employs figurative and ambiguous language. Literary expertise would be beneficial to understanding how meaning and emotion are conveyed in this art form but is often overlooked. We propose placing experts from two dissimilar disciplines – machine learning and literary studies – in conversation to improve the quality of AI writing. Concentrating on evaluation as a vital stage in the text generation process, the study demonstrates that benefit could be derived from literary theoretical perspectives. This knowledge would improve algorithm design and enable a deeper understanding of how AI learns and generates.
This article appears in the special track on AI and Society.