最近的机器学习进展创造了解决生活科学问题的新的强大工具。本文的目的是讨论人工智能（AI）执行的基因推荐的潜在优势。确实，基因推荐引擎试图解决此问题：如果用户对一组基因感兴趣，那么其他基因可能与起始集有关，应该研究？该任务是通过自定义深度学习推荐引擎Deepprophet2（DP2）解决的，该引擎可通过www.generecommender.com在全球研究人员免费获得。此后，说明了算法背后的见解及其实际应用。可以通过将基因映射到可以定义距离以表示它们之间的真实语义距离的度量空间来解决基因推荐问题。为了实现这一目标，基于变压器的模型已在PubMed的一个自由策划的纸质语料库上进行了培训。该论文描述了用于获得最佳偏见变化权衡的多个优化程序，重点是嵌入尺寸和网络深度。在这种情况下，通过交叉验证评估了模型发现与疾病和途径有关的基因集的能力。一个简单的假设指导了该过程：网络没有直接了解途径和疾病的知识，而是学会了基因的相似性及其之间的相互作用。此外，为了进一步研究神经网络代表基因的空间，嵌入的维度减少了，结果被投影到了可忽视的空间上。总之，一组用例说明了该算法在真实单词设置中的潜在应用。

Autoregressive processes naturally arise in a large variety of real-world scenarios, including e.g., stock markets, sell forecasting, weather prediction, advertising, and pricing. When addressing a sequential decision-making problem in such a context, the temporal dependence between consecutive observations should be properly accounted for converge to the optimal decision policy. In this work, we propose a novel online learning setting, named Autoregressive Bandits (ARBs), in which the observed reward follows an autoregressive process of order $k$, whose parameters depend on the action the agent chooses, within a finite set of $n$ actions. Then, we devise an optimistic regret minimization algorithm AutoRegressive Upper Confidence Bounds (AR-UCB) that suffers regret of order $\widetilde{\mathcal{O}} \left( \frac{(k+1)^{3/2}\sqrt{nT}}{(1-\Gamma)^2} \right)$, being $T$ the optimization horizon and $\Gamma < 1$ an index of the stability of the system. Finally, we present a numerical validation in several synthetic and one real-world setting, in comparison with general and specific purpose bandit baselines showing the advantages of the proposed approach.

Behavioral Cloning (BC) aims at learning a policy that mimics the behavior demonstrated by an expert. The current theoretical understanding of BC is limited to the case of finite actions. In this paper, we study BC with the goal of providing theoretical guarantees on the performance of the imitator policy in the case of continuous actions. We start by deriving a novel bound on the performance gap based on Wasserstein distance, applicable for continuous-action experts, holding under the assumption that the value function is Lipschitz continuous. Since this latter condition is hardy fulfilled in practice, even for Lipschitz Markov Decision Processes and policies, we propose a relaxed setting, proving that value function is always Holder continuous. This result is of independent interest and allows obtaining in BC a general bound for the performance of the imitator policy. Finally, we analyze noise injection, a common practice in which the expert action is executed in the environment after the application of a noise kernel. We show that this practice allows deriving stronger performance guarantees, at the price of a bias due to the noise addition.

First-person vision is gaining interest as it offers a unique viewpoint on people's interaction with objects, their attention, and even intention. However, progress in this challenging domain has been relatively slow due to the lack of sufficiently large datasets. In this paper, we introduce EPIC-KITCHENS, a large-scale egocentric video benchmark recorded by 32 participants in their native kitchen environments. Our videos depict non-scripted daily activities: we simply asked each participant to start recording every time they entered their kitchen. Recording took place in 4 cities (in North America and Europe) by participants belonging to 10 different nationalities, resulting in highly diverse cooking styles. Our dataset features 55 hours of video consisting of 11.5M frames, which we densely labelled for a total of 39.6K action segments and 454.3K object bounding boxes. Our annotation is unique in that we had the participants narrate their own videos (after recording), thus reflecting true intention, and we crowd-sourced ground-truths based on these. We describe our object, action and anticipation challenges, and evaluate several baselines over two test splits, seen and unseen kitchens.

An Anomaly Detection (AD) System for Self-diagnosis has been developed for Multiphase Flow Meter (MPFM). The system relies on machine learning algorithms for time series forecasting, historical data have been used to train a model and to predict the behavior of a sensor and, thus, to detect anomalies.

Many challenging reinforcement learning (RL) problems require designing a distribution of tasks that can be applied to train effective policies. This distribution of tasks can be specified by the curriculum. A curriculum is meant to improve the results of learning and accelerate it. We introduce Success Induced Task Prioritization (SITP), a framework for automatic curriculum learning, where a task sequence is created based on the success rate of each task. In this setting, each task is an algorithmically created environment instance with a unique configuration. The algorithm selects the order of tasks that provide the fastest learning for agents. The probability of selecting any of the tasks for the next stage of learning is determined by evaluating its performance score in previous stages. Experiments were carried out in the Partially Observable Grid Environment for Multiple Agents (POGEMA) and Procgen benchmark. We demonstrate that SITP matches or surpasses the results of other curriculum design methods. Our method can be implemented with handful of minor modifications to any standard RL framework and provides useful prioritization with minimal computational overhead.

This paper presents a solution to the GenChal 2022 shared task dedicated to feedback comment generation for writing learning. In terms of this task given a text with an error and a span of the error, a system generates an explanatory note that helps the writer (language learner) to improve their writing skills. Our solution is based on fine-tuning the T5 model on the initial dataset augmented according to syntactical dependencies of the words located within indicated error span. The solution of our team "nigula" obtained second place according to manual evaluation by the organizers.

The task of reconstructing 3D human motion has wideranging applications. The gold standard Motion capture (MoCap) systems are accurate but inaccessible to the general public due to their cost, hardware and space constraints. In contrast, monocular human mesh recovery (HMR) methods are much more accessible than MoCap as they take single-view videos as inputs. Replacing the multi-view Mo- Cap systems with a monocular HMR method would break the current barriers to collecting accurate 3D motion thus making exciting applications like motion analysis and motiondriven animation accessible to the general public. However, performance of existing HMR methods degrade when the video contains challenging and dynamic motion that is not in existing MoCap datasets used for training. This reduces its appeal as dynamic motion is frequently the target in 3D motion recovery in the aforementioned applications. Our study aims to bridge the gap between monocular HMR and multi-view MoCap systems by leveraging information shared across multiple video instances of the same action. We introduce the Neural Motion (NeMo) field. It is optimized to represent the underlying 3D motions across a set of videos of the same action. Empirically, we show that NeMo can recover 3D motion in sports using videos from the Penn Action dataset, where NeMo outperforms existing HMR methods in terms of 2D keypoint detection. To further validate NeMo using 3D metrics, we collected a small MoCap dataset mimicking actions in Penn Action,and show that NeMo achieves better 3D reconstruction compared to various baselines.

Model calibration, which is concerned with how frequently the model predicts correctly, not only plays a vital part in statistical model design, but also has substantial practical applications, such as optimal decision-making in the real world. However, it has been discovered that modern deep neural networks are generally poorly calibrated due to the overestimation (or underestimation) of predictive confidence, which is closely related to overfitting. In this paper, we propose Annealing Double-Head, a simple-to-implement but highly effective architecture for calibrating the DNN during training. To be precise, we construct an additional calibration head-a shallow neural network that typically has one latent layer-on top of the last latent layer in the normal model to map the logits to the aligned confidence. Furthermore, a simple Annealing technique that dynamically scales the logits by calibration head in training procedure is developed to improve its performance. Under both the in-distribution and distributional shift circumstances, we exhaustively evaluate our Annealing Double-Head architecture on multiple pairs of contemporary DNN architectures and vision and speech datasets. We demonstrate that our method achieves state-of-the-art model calibration performance without post-processing while simultaneously providing comparable predictive accuracy in comparison to other recently proposed calibration methods on a range of learning tasks.

Data-driven soft sensors are extensively used in industrial and chemical processes to predict hard-to-measure process variables whose real value is difficult to track during routine operations. The regression models used by these sensors often require a large number of labeled examples, yet obtaining the label information can be very expensive given the high time and cost required by quality inspections. In this context, active learning methods can be highly beneficial as they can suggest the most informative labels to query. However, most of the active learning strategies proposed for regression focus on the offline setting. In this work, we adapt some of these approaches to the stream-based scenario and show how they can be used to select the most informative data points. We also demonstrate how to use a semi-supervised architecture based on orthogonal autoencoders to learn salient features in a lower dimensional space. The Tennessee Eastman Process is used to compare the predictive performance of the proposed approaches.