اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدIs Discriminator a Good Feature Extractor?
85
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The discriminator from generative adversarial nets (GAN) has been used by researchers as a feature extractor in transfer learning and appeared worked well. However, there are also studies that believe this is the wrong research direction because intuitively the task of the discriminator focuses on separating the real samples from the generated ones, making features extracted in this way useless for most of the downstream tasks. To avoid this dilemma, we first conducted a thorough theoretical analysis of the relationship between the discriminator task and the features extracted. We found that the connection between the task of the discriminator and the feature is not as strong as was thought, for that the main factor restricting the feature learned by the discriminator is not the task, but is the need to prevent the entire GAN model from mode collapse during the training. From this perspective and combined with further analyses, we found that to avoid mode collapse, the features extracted by the discriminator are not guided to be different for the real samples, but divergence without noise is indeed allowed and occupies a large proportion of the feature space. This makes the features more robust and helps answer the question as to why the discriminator can succeed as a feature extractor in related research. Consequently, to expose the essence of the discriminator extractor as different from other extractors, we analyze the counterpart of the discriminator extractor, the classifier extractor that assigns the target samples to different categories. We found the performance of the discriminator extractor may be inferior to the classifier based extractor when the source classification task is similar to the target task, which is the common case, but the ability to avoid noise prevents the discriminator from being replaced by the classifier.
قيم البحث
اقرأ أيضاً
We propose a Variational Time Series Feature Extractor (VTSFE), inspired by the VAE-DMP model of Chen et al., to be used for action recognition and prediction. Our method is based on variational autoencoders. It improves VAE-DMP in that it has a bett
er noise inference model, a simpler transition model constraining the acceleration in the trajectories of the latent space, and a tighter lower bound for the variational inference. We apply the method for classification and prediction of whole-body movements on a dataset with 7 tasks and 10 demonstrations per task, recorded with a wearable motion capture suit. The comparison with VAE and VAE-DMP suggests the better performance of our method for feature extraction. An open-source software implementation of each method with TensorFlow is also provided. In addition, a more detailed version of this work can be found in the indicated code repository. Although it was meant to, the VTSFE hasnt been tested for action prediction, due to a lack of time in the context of Maxime Chaveroches Master thesis at INRIA.
Given a sufficiently large amount of labeled data, the non-convex low-rank matrix recovery problem contains no spurious local minima, so a local optimization algorithm is guaranteed to converge to a global minimum starting from any initial guess. How
ever, the actual amount of data needed by this theoretical guarantee is very pessimistic, as it must prevent spurious local minima from existing anywhere, including at adversarial locations. In contrast, prior work based on good initial guesses have more realistic data requirements, because they allow spurious local minima to exist outside of a neighborhood of the solution. In this paper, we quantify the relationship between the quality of the initial guess and the corresponding reduction in data requirements. Using the restricted isometry constant as a surrogate for sample complexity, we compute a sharp threshold number of samples needed to prevent each specific point on the optimization landscape from becoming a spurious local minimum. Optimizing the threshold over regions of the landscape, we see that for initial points around the ground truth, a linear improvement in the quality of the initial guess amounts to a constant factor improvement in the sample complexity.
It is difficult to be able to imitate well in unknown states from a small amount of expert data and sampling data. Supervised learning methods such as Behavioral Cloning do not require sampling data, but usually suffer from distribution shift. The me
thods based on reinforcement learning, such as inverse reinforcement learning and generative adversarial imitation learning (GAIL), can learn from only a few expert data. However, they often need to interact with the environment. Soft Q imitation learning addressed the problems, and it was shown that it could learn efficiently by combining Behavioral Cloning and soft Q-learning with constant rewards. In order to make this algorithm more robust to distribution shift, we propose Discriminator Soft Actor Critic (DSAC). It uses a reward function based on adversarial inverse reinforcement learning instead of constant rewards. We evaluated it on PyBullet environments with only four expert trajectories.
Deep neural networks are typically initialized with random weights, with variances chosen to facilitate signal propagation and stable gradients. It is also believed that diversity of features is an important property of these initializations. We cons
truct a deep convolutional network with identical features by initializing almost all the weights to $0$. The architecture also enables perfect signal propagation and stable gradients, and achieves high accuracy on standard benchmarks. This indicates that random, diverse initializations are textit{not} necessary for training neural networks. An essential element in training this network is a mechanism of symmetry breaking; we study this phenomenon and find that standard GPU operations, which are non-deterministic, can serve as a sufficient source of symmetry breaking to enable training.
Since the early 1980s, the research community has developed ever more sophisticated algorithms for the problem of energy disaggregation, but despite decades of research, there is still a dearth of applications with demonstrated value. In this work, w
e explore a question that is highly pertinent to this research community: how good does energy disaggregation need to be in order to infer characteristics of a household? We present novel techniques that use unsupervised energy disaggregation to predict both household occupancy and static properties of the household such as size of the home and number of occupants. Results show that basic disaggregation approaches performs up to 30% better at occupancy estimation than using aggregate power data alone, and are up to 10% better at estimating static household characteristics. These results show that even rudimentary energy disaggregation techniques are sufficient for improved inference of household characteristics. To conclude, we re-evaluate the bar set by the community for energy disaggregation accuracy and try to answer the question how good is good enough?
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
