اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدInterpretable and Pedagogical Examples
55
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Teachers intentionally pick the most informative examples to show their students. However, if the teacher and student are neural networks, the examples that the teacher network learns to give, although effective at teaching the student, are typically uninterpretable. We show that training the student and teacher iteratively, rather than jointly, can produce interpretable teaching strategies. We evaluate interpretability by (1) measuring the similarity of the teachers emergent strategies to intuitive strategies in each domain and (2) conducting human experiments to evaluate how effective the teachers strategies are at teaching humans. We show that the teacher network learns to select or generate interpretable, pedagogical examples to teach rule-based, probabilistic, boolean, and hierarchical concepts.
قيم البحث
اقرأ أيضاً
The Greens function method has applications in several fields in Physics, from classical differential equations to quantum many-body problems. In the quantum context, Greens functions are correlation functions, from which it is possible to extract in
formation from the system under study, such as the density of states, relaxation times and response functions. Despite its power and versatility, it is known as a laborious and sometimes cumbersome method. Here we introduce the equilibrium Greens functions and the equation-of-motion technique, exemplifying the method in discrete lattices of non-interacting electrons. We start with simple models, such as the two-site molecule, the infinite and semi-infinite one-dimensional chains, and the two-dimensional ladder. Numerical implementations are developed via the recursive Greens function, implemented in Julia, an open-source, efficient and easy-to-learn scientific language. We also present a new variation of the surface recursive Greens function method, which can be of interest when simulating simultaneously the properties of surface and bulk.
Deep neural networks (DNNs) have demonstrated impressive performance on a wide array of tasks, but they are usually considered opaque since internal structure and learned parameters are not interpretable. In this paper, we re-examine the internal rep
resentations of DNNs using adversarial images, which are generated by an ensemble-optimization algorithm. We find that: (1) the neurons in DNNs do not truly detect semantic objects/parts, but respond to objects/parts only as recurrent discriminative patches; (2) deep visual representations are not robust distributed codes of visual concepts because the representations of adversarial images are largely not consistent with those of real images, although they have similar visual appearance, both of which are different from previous findings. To further improve the interpretability of DNNs, we propose an adversarial training scheme with a consistent loss such that the neurons are endowed with human-interpretable concepts. The induced interpretable representations enable us to trace eventual outcomes back to influential neurons. Therefore, human users can know how the models make predictions, as well as when and why they make errors.
Machine learning models are increasingly used in the industry to make decisions such as credit insurance approval. Some people may be tempted to manipulate specific variables, such as the age or the salary, in order to get better chances of approval.
In this ongoing work, we propose to discuss, with a first proposition, the issue of detecting a potential local adversarial example on classical tabular data by providing to a human expert the locally critical features for the classifiers decision, in order to control the provided information and avoid a fraud.
Questions that require counting a variety of objects in images remain a major challenge in visual question answering (VQA). The most common approaches to VQA involve either classifying answers based on fixed length representations of both the image a
nd question or summing fractional counts estimated from each section of the image. In contrast, we treat counting as a sequential decision process and force our model to make discrete choices of what to count. Specifically, the model sequentially selects from detected objects and learns interactions between objects that influence subsequent selections. A distinction of our approach is its intuitive and interpretable output, as discrete counts are automatically grounded in the image. Furthermore, our method outperforms the state of the art architecture for VQA on multiple metrics that evaluate counting.
Given the pressing need for assuring algorithmic transparency, Explainable AI (XAI) has emerged as one of the key areas of AI research. In this paper, we develop a novel Bayesian extension to the LIME framework, one of the most widely used approaches
in XAI -- which we call BayLIME. Compared to LIME, BayLIME exploits prior knowledge and Bayesian reasoning to improve both the consistency in repeated explanations of a single prediction and the robustness to kernel settings. BayLIME also exhibits better explanation fidelity than the state-of-the-art (LIME, SHAP and GradCAM) by its ability to integrate prior knowledge from, e.g., a variety of other XAI techniques, as well as verification and validation (V&V) methods. We demonstrate the desirable properties of BayLIME through both theoretical analysis and extensive experiments.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
