Knowledge distillation Soft labeling becomes a common output regularization (Hinton et al., 2015), a kind of soft labeling (Yuan et al., for generalization and model compression 2019), can compress the size of a teacher model, or improve of deep neural networks. However, the effect the accuracy of its student networks (Xie et al., 2019). of soft labeling on out-of-distribution (OOD) detection, which is an important topic of machine Despite the popularity of soft labeling, how soft labeling learning safety, is not explored. In this study, we affects OOD detection of DNNs has not been explored. In show that soft labeling can determine OOD detection this study, we assume that regularizing predictions on incorrect performance. Specifically, how to regularize classes by soft labeling determines OOD detection outputs of incorrect classes by soft labeling can performance of DNNs. We analyze and empirically verify deteriorate or improve OOD detection. Based on our assumption, based on two major results: a) label the empirical results, we postulate a future work smoothing deteriorates OOD detection of DNNs, and b) for OOD-robust DNNs: a proper output regularization soft labels, generated by a teacher model, distill OOD detection by soft labeling can construct OOD-robust performance into its student models. In particular, DNNs without additional training of OOD samples the degraded test accuracy of a teacher model with outlier or modifying the models, while improving exposure is recovered or improved in its student models, classification accuracy.

Fine-tuning the deep convolution neural network(CNN) using a pre-trained model helps transfer knowledge learned from larger datasets to the target task. While the accuracy could be largely improved even when the training dataset is small, the transfer learning outcome is usually constrained by the pre-trained model with close CNN weights (Liu et al., 2019), as the backpropagation here brings smaller updates to deeper CNN layers. In this work, we propose RIFLE - a simple yet effective strategy that deepens backpropagation in transfer learning settings, through periodically Re-Initializing the Fully-connected LayEr with random scratch during the fine-tuning procedure. RIFLE brings meaningful updates to the weights of deep CNN layers and improves low-level feature learning, while the effects of randomization can be easily converged throughout the overall learning procedure. The experiments show that the use of RIFLE significantly improves deep transfer learning accuracy on a wide range of datasets, out-performing known tricks for the similar purpose, such as Dropout, DropConnect, StochasticDepth, Disturb Label and Cyclic Learning Rate, under the same settings with 0.5% -2% higher testing accuracy. Empirical cases and ablation studies further indicate RIFLE brings meaningful updates to deep CNN layers with accuracy improved.

The ability to conduct logical reasoning is a fundamental aspect of intelligent human behavior, and thus an important problem along the way to human-level artificial intelligence. Traditionally, logic-based symbolic methods from the field of knowledge representation and reasoning have been used to equip agents with capabilities that resemble human logical reasoning qualities. More recently, however, there has been an increasing interest in using machine learning rather than logic-based symbolic formalisms to tackle these tasks. In this paper, we employ state-of-the-art methods for training deep neural networks to devise a novel model that is able to learn how to effectively perform logical reasoning in the form of basic ontology reasoning. This is an important and at the same time very natural logical reasoning task, which is why the presented approach is applicable to a plethora of important real-world problems. We present the outcomes of several experiments, which show that our model is able to learn to perform highly accurate ontology reasoning on very large, diverse, and challenging benchmarks. Furthermore, it turned out that the suggested approach suffers much less from different obstacles that prohibit logic-based symbolic reasoning, and, at the same time, is surprisingly plausible from a biological point of view.

Developing secure machine learning models from adversarial examples is challenging as various methods are continually being developed to generate adversarial attacks. In this work, we propose an evolutionary approach to automatically determine Image Processing Techniques Sequence (IPTS) for detecting malicious inputs. Accordingly, we first used a diverse set of attack methods including adaptive attack methods (on our defense) to generate adversarial samples from the clean dataset. A detection framework based on a genetic algorithm (GA) is developed to find the optimal IPTS, where the optimality is estimated by different fitness measures such as Euclidean distance, entropy loss, average histogram, local binary pattern and loss functions. The "image difference" between the original and processed images is used to extract the features, which are then fed to a classification scheme in order to determine whether the input sample is adversarial or clean. This paper described our methodology and performed experiments using multiple data-sets tested with several adversarial attacks. For each attack-type and dataset, it generates unique IPTS. A set of IPTS selected dynamically in testing time which works as a filter for the adversarial attack. Our empirical experiments exhibited promising results indicating the approach can efficiently be used as processing for any AI model.

In this paper, we introduce multi-resolution interest interests based on their historical behaviors. Most of recent advances fusion model (MRIF) composed of interest extraction layer, interest in recommender systems mainly focus on modeling users' aggregation layer, and attentional fusion structure, which addresses preferences accurately using deep learning based approaches. There the problem of extracting users' preferences at different temporalranges are two important properties of users' interests, one is that users' and combining multi-resolution interests effectively. The interests are dynamic and evolve over time, the other is that users' main contributions are: interests have different resolutions, or temporal-ranges to be precise, such as long-term and short-term preferences. Existing approaches - We design a new network structure to model the dynamic either use Recurrent Neural Networks (RNNs) to address changes and different temporal-ranges of users' interests, the drifts in users' interests without considering different temporalranges, which yields more accurate prediction results than extracting or design two different networks to model long-term and main interest directly from interaction sequences.

Deep neural networks are capable of training fast and generalizing well within many domains. Despite their promising performance, deep networks have shown sensitivities to perturbations of their inputs (e.g., adversarial examples) and their learned feature representations are often difficult to interpret, raising concerns about their true capability and trustworthiness. Recent work in adversarial training, a form of robust optimization in which the model is optimized against adversarial examples, demonstrates the ability to improve performance sensitivities to perturbations and yield feature representations that are more interpretable. Adversarial training, however, comes with an increased computational cost over that of standard (i.e., nonrobust) training, rendering it impractical for use in large-scale problems. Recent work suggests that a fast approximation to adversarial training shows promise for reducing training time and maintaining robustness in the presence of perturbations bounded by the infinity norm. In this work, we demonstrate that this approach extends to the Euclidean norm and preserves the human-aligned feature representations that are common for robust models. Additionally, we show that using a distributed training scheme can further reduce the time to train robust deep networks. Fast adversarial training is a promising approach that will provide increased security and explainability in machine learning applications for which robust optimization was previously thought to be impractical.

For the challenging computational environment of IOT/edge computing, personalized federated learning allows every client to train a strong personalized cloud model by effectively collaborating with the other clients in a privacy-preserving manner. The performance of personalized federated learning is largely determined by the effectiveness of inter-client collaboration. However, when the data is non-IID across all clients, it is challenging to infer the collaboration relationships between clients without knowing their data distributions. In this paper, we propose to tackle this problem by a novel framework named federated attentive message passing (FedAMP) that allows each client to collaboratively train its own personalized cloud model without using a global model. FedAMP implements an attentive collaboration mechanism by iteratively encouraging clients with more similar model parameters to have stronger collaborations. This adaptively discovers the underlying collaboration relationships between clients, which significantly boosts effectiveness of collaboration and leads to the outstanding performance of FedAMP. We establish the convergence of FedAMP for both convex and non-convex models, and further propose a heuristic method that resembles the FedAMP framework to further improve its performance for federated learning with deep neural networks. Extensive experiments demonstrate the superior performance of our methods in handling non-IID data, dirty data and dropped clients.

In this essay, we explore a point of intersection between deep learning and neuroscience, through the lens of large language models, transfer learning and network compression. Just like perceptual and cognitive neurophysiology has inspired effective deep neural network architectures which in turn make a useful model for understanding the brain, here we explore how biological neural development might inspire efficient and robust optimization procedures which in turn serve as a useful model for the maturation and aging of the brain. Hopefully it would inspire the reader in one way or two, or at the very least, kill some boredom during a global pandemic. We are going to touch on the following topics through the lens of large language models: - How do overparameterized deep neural nets generalize? - How does transfer learning help generalization? Before we start, it is prudent to say a few words about the brain metaphor, to clarify this author's position on the issue as it often arises central at debates. The confluence of deep learning and neuroscience arguably took place as early as the conception of artificial neural nets, because artificial neurons abstract characteristic behaviors of biological ones (McCulloch and Pitts, 1943).

Federated Learning (FL) allows a set of agents to collaboratively train a model in a decentralized fashion without sharing their potentially sensitive data. This makes FL suitable for privacy-preserving applications. At the same time, FL is susceptible to adversarial attacks due to decentralized and unvetted data. One important line of attacks against FL is the backdoor attacks. In a backdoor attack, an adversary tries to embed a backdoor trigger functionality to the model during training which can later be activated to cause a desired misclassification. To prevent such backdoor attacks, we propose a lightweight defense that requires no change to the FL structure. At a high level, our defense is based on carefully adjusting the server's learning rate, per dimension, at each round based on the sign information of agent's updates. We first conjecture the necessary steps to carry a successful backdoor attack in FL setting, and then, explicitly formulate the defense based on our conjecture. Through experiments, we provide empirical evidence to the support of our conjecture. We test our defense against backdoor attacks under different settings, and, observe that either backdoor is completely eliminated, or its accuracy is significantly reduced. Overall, our experiments suggests that our approach significantly outperforms some of the recently proposed defenses in the literature. We achieve this by having minimal influence over the accuracy of the trained models.

Learning to control a safety-critical system with latent dynamics (e.g. for deep brain stimulation) requires taking calculated risks to gain information as efficiently as possible. To address this problem, we present a probabilistically-safe, meta-active learning approach to efficiently learn system dynamics and optimal configurations. We cast this problem as meta-learning an acquisition function, which is represented by a Long-Short Term Memory Network (LSTM) encoding sampling history. This acquisition function is meta-learned offline to learn high quality sampling strategies. We employ a mixed-integer linear program as our policy with the final, linearized layers of our LSTM acquisition function directly encoded into the objective to trade off expected information gain (e.g., improvement in the accuracy of the model of system dynamics) with the likelihood of safe control. We set a new state-of-the-art in active learning for control of a high-dimensional system with altered dynamics (i.e., a damaged aircraft), achieving a 46% increase in information gain and a 20% speedup in computation time over baselines. Furthermore, we demonstrate our system's ability to learn the optimal parameter settings for deep brain stimulation in a rat's brain while avoiding unwanted side effects (i.e., triggering seizures), outperforming prior state-of-the-art approaches with a 58% increase in information gain. Additionally, our algorithm achieves a 97% likelihood of terminating in a safe state while losing only 15% of information gain.