To train a deep neural network to mimic the outcomes of processing sequences, a version of Conditional Generalized Adversarial Network (CGAN) can be used. It has been observed by others that CGAN can help to improve the results even for deterministic sequences, where only one output is associated with the processing of a given input. Surprisingly, our CGAN-based tests on deterministic geophysical processing sequences did not produce a real improvement compared to the use of an $L_p$ loss; we here propose a first theoretical explanation why. Our analysis goes from the non-deterministic case to the deterministic one. It led us to develop an adversarial way to train a content loss that gave better results on our data.

Agents trained via deep reinforcement learning (RL) routinely fail to generalize to unseen environments, even when these share the same underlying dynamics as the training levels. Understanding the generalization properties of RL is one of the challenges of modern machine learning. Towards this goal, we analyze policy learning in the context of Partially Observable Markov Decision Processes (POMDPs) and formalize the dynamics of training levels as instances. We prove that, independently of the exploration strategy, reusing instances introduces significant changes on the effective Markov dynamics the agent observes during training. Maximizing expected rewards impacts the learned belief state of the agent by inducing undesired instance-specific speed-running policies instead of generalizable ones, which are sub-optimal on the training set. We provide generalization bounds to the value gap in train and test environments based on the number of training instances, and use insights based on these to improve performance on unseen levels. We propose training a shared belief representation over an ensemble of specialized policies, from which we compute a consensus policy that is used for data collection, disallowing instance-specific exploitation. We experimentally validate our theory, observations, and the proposed computational solution over the CoinRun benchmark.

Deep generative networks trained via maximum likelihood on a natural image dataset like CIFAR10 often assign high likelihoods to images from datasets with different objects (e.g., SVHN). We refine previous investigations of this failure at anomaly detection for invertible generative networks and provide a clear explanation of it as a combination of model bias and domain prior: Convolutional networks learn similar low-level feature distributions when trained on any natural image dataset and these low-level features dominate the likelihood. Hence, when the discriminative features between inliers and outliers are on a high-level, e.g., object shapes, anomaly detection becomes particularly challenging. To remove the negative impact of model bias and domain prior on detecting high-level differences, we propose two methods, first, using the log likelihood ratios of two identical models, one trained on the in-distribution data (e.g., CIFAR10) and the other one on a more general distribution of images (e.g., 80 Million Tiny Images). We also derive a novel outlier loss for the in-distribution network on samples from the more general distribution to further improve the performance. Secondly, using a multi-scale model like Glow, we show that low-level features are mainly captured at early scales. Therefore, using only the likelihood contribution of the final scale performs remarkably well for detecting high-level feature differences of the out-of-distribution and the in-distribution. This method is especially useful if one does not have access to a suitable general distribution. Overall, our methods achieve strong anomaly detection performance in the unsupervised setting, and only slightly underperform state-of-the-art classifier-based methods in the supervised setting. Code can be found at https://github.com/boschresearch/hierarchical_anomaly_detection.

Abstract-Waste recycling is an important way of saving This study uses transfer learning from a pre-trained Resnet-energy and materials in the production process. In general 50 model to generate a model which is capable of classifying cases recyclable objects are mixed with unrecyclable objects, images of individual waste objects into the following six which raises a need for identification and classification. To paper proposes a convolutional neural network (CNN) model integrate the model into actual application, which often deals to complete both tasks. The model uses transfer learning with bird's-eye view of piles of waste, a sliding-window process from a pretrained Resnet-50 CNN to complete feature in the pre-classification stage split the image into smaller extraction. A subsequent fully connected layer for fragments for the CNN to process, and the labelled points are classification was trained on the augmented TrashNet dataset integrated with Gaussian Mixture Model in the postclassification [1].

This paper addresses the problem of optimizing partition functions in a stochastic learning setting. We propose a stochastic variant of the bound majorization algorithm from [29] that relies on upperbounding the partition function with a quadratic surrogate. The update of the proposed method, that we refer to as Stochastic Partition Function Bound (SPFB), resembles scaled stochastic gradient descent where the scaling factor relies on a second order term that is however different from the Hessian. Similarly to quasi-Newton schemes, this term is constructed using the stochastic approximation of the value of the function and its gradient. We prove sub-linear convergence rate of the proposed method and show the construction of its low-rank variant (LSPFB). Experiments on logistic regression demonstrate that the proposed schemes significantly outperform SGD. We also discuss how to use quadratic partition function bound for efficient training of deep learning models and in non-convex optimization.

The loss landscapes of deep neural networks are not well understood due to their high nonconvexity. Empirically, the local minima of these loss functions can be connected by a learned curve in model space, along which the loss remains nearly constant; a feature known as mode connectivity. Yet, current curve finding algorithms do not consider the influence of symmetry in the loss surface created by model weight permutations. We propose a more general framework to investigate the effect of symmetry on landscape connectivity by accounting for the weight permutations of the networks being connected. To approximate the optimal permutation, we introduce an inexpensive heuristic referred to as neuron alignment. Neuron alignment promotes similarity between the distribution of intermediate activations of models along the curve. We provide theoretical analysis establishing the benefit of alignment to mode connectivity based on this simple heuristic. We empirically verify that the permutation given by alignment is locally optimal via a proximal alternating minimization scheme. Empirically, optimizing the weight permutation is critical for efficiently learning a simple, planar, low-loss curve between networks that successfully generalizes. Our alignment method can significantly alleviate the recently identified robust loss barrier on the path connecting two adversarial robust models and find more robust and accurate models on the path.

A pre-trained generator has been frequently adopted in compressed sensing (CS) due to its ability to effectively estimate signals with the prior of NNs. In order to further refine the NN-based prior, we propose a framework that allows the generator to utilize additional information from a given measurement for prior learning, thereby yielding more accurate prediction for signals. As our framework has a simple form, it is easily applied to existing CS methods using pre-trained generators. We demonstrate through extensive experiments that our framework exhibits uniformly superior performances by large margin and can reduce the reconstruction error up to an order of magnitude for some applications. We also explain the experimental success in theory by showing that our framework can slightly relax the stringent signal presence condition, which is required to guarantee the success of signal recovery.

Data poisoning and backdoor attacks manipulate training data in order to cause models to fail during inference. A recent survey of industry practitioners found that data poisoning is the number one concern among threats ranging from model stealing to adversarial attacks. However, we find that the impressive performance evaluations from data poisoning attacks are, in large part, artifacts of inconsistent experimental design. Moreover, we find that existing poisoning methods have been tested in contrived scenarios, and many fail in more realistic settings. In order to promote fair comparison in future work, we develop standardized benchmarks for data poisoning and backdoor attacks. Data poisoning is a security threat to machine learning systems in which an attacker controls the behavior of a system by manipulating its training data. This class of threats is particularly germane to deep learning systems because they require large amounts of data to train and are therefore often trained (or pre-trained) on large datasets scraped from the web. For example, the Open Images and the Amazon Products datasets contain approximately 9 million and 233 million samples, respectively, that are scraped from a wide range of potentially insecure, and in many cases unknown, sources (Kuznetsova et al., 2020; Ni, 2018). At this scale, it is often infeasible to properly vet content. Furthermore, many practitioners create datasets by harvesting system inputs (e.g., emails received, files uploaded) or scraping user-created content (e.g., profiles, text messages, advertisements) without any mechanisms to bar malicious actors from contributing data. The dependence of industrial AI systems on datasets that are not manually inspected has led to fear that corrupted training data could produce faulty models (Jiang et al., 2017). In fact, a recent survey of 28 industry organizations found that these companies are significantly more afraid of data poisoning than other threats from adversarial machine learning (Kumar et al., 2020). A spectrum of poisoning attacks exists in the literature. Backdoor data poisoning causes a model to misclassify test-time samples that contain a trigger - a visual feature in images or a particular character sequence in the natural language setting (Chen et al., 2017; Dai et al., 2019; Saha et al., For example, one might tamper with training images so that a vision system fails to identify any person wearing a shirt with the trigger symbol printed on it.

A model must adapt itself to generalize to new and different data during testing. This is the setting of fully test-time adaptation given only unlabeled test data and the model parameters. We propose test-time entropy minimization (tent) for adaptation: we optimize for model confidence as measured by the entropy of its predictions. During testing, we adapt the model features by estimating normalization statistics and optimizing channel-wise affine transformations. Tent improves robustness to corruptions for image classification on ImageNet and CIFAR-10/100 and achieves state-of-the-art error on ImageNet-C for ResNet-50. Tent demonstrates the feasibility of target-only domain adaptation for digit classification from SVHN to MNIST/MNIST-M/USPS and semantic segmentation from GTA to Cityscapes. Deep networks can achieve high accuracy on training and testing data from the same distribution, as evidenced by tremendous benchmark progress (Krizhevsky et al., 2012; Simonyan & Zisserman, 2015; He et al., 2016). However, generalization to new and different data is limited (Hendrycks & Dietterich, 2019; Recht et al., 2019; Geirhos et al., 2018). Accuracy suffers when the training (source) data differ from the testing (target) data, a condition known as dataset shift (Quionero-Candela et al., 2009). Models can be sensitive to shifts during testing that were not known during training, whether natural variations or corruptions, such as unexpected weather or sensor degradation.

Training Neural Ordinary Differential Equations (ODEs) is often computationally expensive. Indeed, computing the forward pass of such models involves solving an ODE which can become arbitrarily complex during training. Recent works have shown that regularizing the dynamics of the ODE can partially alleviate this. In this paper we propose a new regularization technique: randomly sampling the end time of the ODE during training. The proposed regularization is simple to implement, has negligible overhead and is effective across a wide variety of tasks. Further, the technique is orthogonal to several other methods proposed to regularize the dynamics of ODEs and as such can be used in conjunction with them. We show through experiments on normalizing flows, time series models and image recognition that the proposed regularization can significantly decrease training time and even improve performance over baseline models.