扩张的卷积基本上是通过定期插入内核元素之间的空格而创建的更宽内核的卷积。在本文中，我们提出了一种新版本的扩张卷积，其中通过通过插值技术通过反向化进行了学习的间距。我们称这种方法“通过学习间距扩张卷积”（DCLS），并推广其对N维卷积案例的方法。但是，我们这里的主要焦点将是我们开发了两种实现的2D案例：一个天真的外壳：一个天真的一个，它构建了适合小的扩张率的扩张内核，以及使用“IM2COL的修改版本的时间/记忆有效的内核” “ 算法。然后，我们通过DCLS ONE通过简单的替换，我们如何通过简单的替换DCLS替换该技术如何通过简单的替换置换古典扩张的卷积层对Pascal VOC 2012 DataSet上的现有架构的准确性。此外，我们表明DCLS允许减少最近Convmixer架构中使用的深度卷曲的学习参数的数量，其因子3具有NO或非常低的准确性，并且通过用稀疏DCLS替换大型密集内核。该方法的代码基于Pytorch，可用于：https://github.com/k-h-imail/dilated-convolution-with-learnable-pacings-pytorch。

In large-scale machine learning, recent works have studied the effects of compressing gradients in stochastic optimization in order to alleviate the communication bottleneck. These works have collectively revealed that stochastic gradient descent (SGD) is robust to structured perturbations such as quantization, sparsification, and delays. Perhaps surprisingly, despite the surge of interest in large-scale, multi-agent reinforcement learning, almost nothing is known about the analogous question: Are common reinforcement learning (RL) algorithms also robust to similar perturbations? In this paper, we investigate this question by studying a variant of the classical temporal difference (TD) learning algorithm with a perturbed update direction, where a general compression operator is used to model the perturbation. Our main technical contribution is to show that compressed TD algorithms, coupled with an error-feedback mechanism used widely in optimization, exhibit the same non-asymptotic theoretical guarantees as their SGD counterparts. We then extend our results significantly to nonlinear stochastic approximation algorithms and multi-agent settings. In particular, we prove that for multi-agent TD learning, one can achieve linear convergence speedups in the number of agents while communicating just $\tilde{O}(1)$ bits per agent at each time step. Our work is the first to provide finite-time results in RL that account for general compression operators and error-feedback in tandem with linear function approximation and Markovian sampling. Our analysis hinges on studying the drift of a novel Lyapunov function that captures the dynamics of a memory variable introduced by error feedback.

A comprehensive pharmaceutical recommendation system was designed based on the patients and drugs features extracted from Drugs.com and Druglib.com. First, data from these databases were combined, and a dataset of patients and drug information was built. Secondly, the patients and drugs were clustered, and then the recommendation was performed using different ratings provided by patients, and importantly by the knowledge obtained from patients and drug specifications, and considering drug interactions. To the best of our knowledge, we are the first group to consider patients conditions and history in the proposed approach for selecting a specific medicine appropriate for that particular user. Our approach applies artificial intelligence (AI) models for the implementation. Sentiment analysis using natural language processing approaches is employed in pre-processing along with neural network-based methods and recommender system algorithms for modeling the system. In our work, patients conditions and drugs features are used for making two models based on matrix factorization. Then we used drug interaction to filter drugs with severe or mild interactions with other drugs. We developed a deep learning model for recommending drugs by using data from 2304 patients as a training set, and then we used data from 660 patients as our validation set. After that, we used knowledge from critical information about drugs and combined the outcome of the model into a knowledge-based system with the rules obtained from constraints on taking medicine.

Nowadays, the current neural network models of dialogue generation(chatbots) show great promise for generating answers for chatty agents. But they are short-sighted in that they predict utterances one at a time while disregarding their impact on future outcomes. Modelling a dialogue's future direction is critical for generating coherent, interesting dialogues, a need that has led traditional NLP dialogue models that rely on reinforcement learning. In this article, we explain how to combine these objectives by using deep reinforcement learning to predict future rewards in chatbot dialogue. The model simulates conversations between two virtual agents, with policy gradient methods used to reward sequences that exhibit three useful conversational characteristics: the flow of informality, coherence, and simplicity of response (related to forward-looking function). We assess our model based on its diversity, length, and complexity with regard to humans. In dialogue simulation, evaluations demonstrated that the proposed model generates more interactive responses and encourages a more sustained successful conversation. This work commemorates a preliminary step toward developing a neural conversational model based on the long-term success of dialogues.

Autoencoders are a popular model in many branches of machine learning and lossy data compression. However, their fundamental limits, the performance of gradient methods and the features learnt during optimization remain poorly understood, even in the two-layer setting. In fact, earlier work has considered either linear autoencoders or specific training regimes (leading to vanishing or diverging compression rates). Our paper addresses this gap by focusing on non-linear two-layer autoencoders trained in the challenging proportional regime in which the input dimension scales linearly with the size of the representation. Our results characterize the minimizers of the population risk, and show that such minimizers are achieved by gradient methods; their structure is also unveiled, thus leading to a concise description of the features obtained via training. For the special case of a sign activation function, our analysis establishes the fundamental limits for the lossy compression of Gaussian sources via (shallow) autoencoders. Finally, while the results are proved for Gaussian data, numerical simulations on standard datasets display the universality of the theoretical predictions.

Pruning refers to the elimination of trivial weights from neural networks. The sub-networks within an overparameterized model produced after pruning are often called Lottery tickets. This research aims to generate winning lottery tickets from a set of lottery tickets that can achieve similar accuracy to the original unpruned network. We introduce a novel winning ticket called Cyclic Overlapping Lottery Ticket (COLT) by data splitting and cyclic retraining of the pruned network from scratch. We apply a cyclic pruning algorithm that keeps only the overlapping weights of different pruned models trained on different data segments. Our results demonstrate that COLT can achieve similar accuracies (obtained by the unpruned model) while maintaining high sparsities. We show that the accuracy of COLT is on par with the winning tickets of Lottery Ticket Hypothesis (LTH) and, at times, is better. Moreover, COLTs can be generated using fewer iterations than tickets generated by the popular Iterative Magnitude Pruning (IMP) method. In addition, we also notice COLTs generated on large datasets can be transferred to small ones without compromising performance, demonstrating its generalizing capability. We conduct all our experiments on Cifar-10, Cifar-100 & TinyImageNet datasets and report superior performance than the state-of-the-art methods.

Performance metrics-driven context caching has a profound impact on throughput and response time in distributed context management systems for real-time context queries. This paper proposes a reinforcement learning based approach to adaptively cache context with the objective of minimizing the cost incurred by context management systems in responding to context queries. Our novel algorithms enable context queries and sub-queries to reuse and repurpose cached context in an efficient manner. This approach is distinctive to traditional data caching approaches by three main features. First, we make selective context cache admissions using no prior knowledge of the context, or the context query load. Secondly, we develop and incorporate innovative heuristic models to calculate expected performance of caching an item when making the decisions. Thirdly, our strategy defines a time-aware continuous cache action space. We present two reinforcement learning agents, a value function estimating actor-critic agent and a policy search agent using deep deterministic policy gradient method. The paper also proposes adaptive policies such as eviction and cache memory scaling to complement our objective. Our method is evaluated using a synthetically generated load of context sub-queries and a synthetic data set inspired from real world data and query samples. We further investigate optimal adaptive caching configurations under different settings. This paper presents, compares, and discusses our findings that the proposed selective caching methods reach short- and long-term cost- and performance-efficiency. The paper demonstrates that the proposed methods outperform other modes of context management such as redirector mode, and database mode, and cache all policy by up to 60% in cost efficiency.

We address interactive panoptic annotation, where one segment all object and stuff regions in an image. We investigate two graph-based segmentation algorithms that both enforce connectivity of each region, with a notable class-aware Integer Linear Programming (ILP) formulation that ensures global optimum. Both algorithms can take RGB, or utilize the feature maps from any DCNN, whether trained on the target dataset or not, as input. We then propose an interactive, scribble-based annotation framework.

We introduce an information-maximization approach for the Generalized Category Discovery (GCD) problem. Specifically, we explore a parametric family of loss functions evaluating the mutual information between the features and the labels, and find automatically the one that maximizes the predictive performances. Furthermore, we introduce the Elbow Maximum Centroid-Shift (EMaCS) technique, which estimates the number of classes in the unlabeled set. We report comprehensive experiments, which show that our mutual information-based approach (MIB) is both versatile and highly competitive under various GCD scenarios. The gap between the proposed approach and the existing methods is significant, more so when dealing with fine-grained classification problems. Our code: \url{https://github.com/fchiaroni/Mutual-Information-Based-GCD}.

Recent studies have revealed that, beyond conventional accuracy, calibration should also be considered for training modern deep neural networks. To address miscalibration during learning, some methods have explored different penalty functions as part of the learning objective, alongside a standard classification loss, with a hyper-parameter controlling the relative contribution of each term. Nevertheless, these methods share two major drawbacks: 1) the scalar balancing weight is the same for all classes, hindering the ability to address different intrinsic difficulties or imbalance among classes; and 2) the balancing weight is usually fixed without an adaptive strategy, which may prevent from reaching the best compromise between accuracy and calibration, and requires hyper-parameter search for each application. We propose Class Adaptive Label Smoothing (CALS) for calibrating deep networks, which allows to learn class-wise multipliers during training, yielding a powerful alternative to common label smoothing penalties. Our method builds on a general Augmented Lagrangian approach, a well-established technique in constrained optimization, but we introduce several modifications to tailor it for large-scale, class-adaptive training. Comprehensive evaluation and multiple comparisons on a variety of benchmarks, including standard and long-tailed image classification, semantic segmentation, and text classification, demonstrate the superiority of the proposed method. The code is available at https://github.com/by-liu/CALS.