机器人经常面临抓住目标对象的情况，但由于其他当前物体阻止了掌握动作。我们提出了一种深入的强化学习方法，以学习掌握和推动政策，以在高度混乱的环境中操纵目标对象以解决这个问题。特别是，提出了双重强化学习模型方法，该方法在处理复杂场景时具有很高的弹性，在模拟环境中使用原始对象平均达到98％的任务完成。为了评估所提出方法的性能，我们在包装对象和一堆对象方案中进行了两组实验集，在模拟中总共进行了1000个测试。实验结果表明，该提出的方法在各种情况下都效果很好，并且表现出了最新的最新方法。演示视频，训练有素的模型和源代码可重复可重复性目的。 https://github.com/kamalnl92/self-superist-learning-for-pushing-and-grasping。

According to the latest trend of artificial intelligence, AI-systems needs to clarify regarding general,specific decisions,services provided by it. Only consumer is satisfied, with explanation , for example, why any classification result is the outcome of any given time. This actually motivates us using explainable or human understandable AI for a behavioral mining scenario, where users engagement on digital platform is determined from context, such as emotion, activity, weather, etc. However, the output of AI-system is not always systematically correct, and often systematically correct, but apparently not-perfect and thereby creating confusions, such as, why the decision is given? What is the reason underneath? In this context, we first formulate the behavioral mining problem in deep convolutional neural network architecture. Eventually, we apply a recursive neural network due to the presence of time-series data from users physiological and environmental sensor-readings. Once the model is developed, explanations are presented with the advent of XAI models in front of users. This critical step involves extensive trial with users preference on explanations over conventional AI, judgement of credibility of explanation.

Enterprise resource planning (ERP) software brings resources, data together to keep software-flow within business processes in a company. However, cloud computing's cheap, easy and quick management promise pushes business-owners for a transition from monolithic to a data-center/cloud based ERP. Since cloud-ERP development involves a cyclic process, namely planning, implementing, testing and upgrading, its adoption is realized as a deep recurrent neural network problem. Eventually, a classification algorithm based on long short term memory (LSTM) and TOPSIS is proposed to identify and rank, respectively, adoption features. Our theoretical model is validated over a reference model by articulating key players, services, architecture, functionalities. Qualitative survey is conducted among users by considering technology, innovation and resistance issues, to formulate hypotheses on key adoption factors.

Before the transition of AVs to urban roads and subsequently unprecedented changes in traffic conditions, evaluation of transportation policies and futuristic road design related to pedestrian crossing behavior is of vital importance. Recent studies analyzed the non-causal impact of various variables on pedestrian waiting time in the presence of AVs. However, we mainly investigate the causal effect of traffic density on pedestrian waiting time. We develop a Double/Debiased Machine Learning (DML) model in which the impact of confounders variable influencing both a policy and an outcome of interest is addressed, resulting in unbiased policy evaluation. Furthermore, we try to analyze the effect of traffic density by developing a copula-based joint model of two main components of pedestrian crossing behavior, pedestrian stress level and waiting time. The copula approach has been widely used in the literature, for addressing self-selection problems, which can be classified as a causality analysis in travel behavior modeling. The results obtained from copula approach and DML are compared based on the effect of traffic density. In DML model structure, the standard error term of density parameter is lower than copula approach and the confidence interval is considerably more reliable. In addition, despite the similar sign of effect, the copula approach estimates the effect of traffic density lower than DML, due to the spurious effect of confounders. In short, the DML model structure can flexibly adjust the impact of confounders by using machine learning algorithms and is more reliable for planning future policies.

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.

Handwriting Recognition has been a field of great interest in the Artificial Intelligence domain. Due to its broad use cases in real life, research has been conducted widely on it. Prominent work has been done in this field focusing mainly on Latin characters. However, the domain of Arabic handwritten character recognition is still relatively unexplored. The inherent cursive nature of the Arabic characters and variations in writing styles across individuals makes the task even more challenging. We identified some probable reasons behind this and proposed a lightweight Convolutional Neural Network-based architecture for recognizing Arabic characters and digits. The proposed pipeline consists of a total of 18 layers containing four layers each for convolution, pooling, batch normalization, dropout, and finally one Global average pooling and a Dense layer. Furthermore, we thoroughly investigated the different choices of hyperparameters such as the choice of the optimizer, kernel initializer, activation function, etc. Evaluating the proposed architecture on the publicly available 'Arabic Handwritten Character Dataset (AHCD)' and 'Modified Arabic handwritten digits Database (MadBase)' datasets, the proposed model respectively achieved an accuracy of 96.93% and 99.35% which is comparable to the state-of-the-art and makes it a suitable solution for real-life end-level applications.

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs. The only human oversight is provided through a list of rules or principles, and so we refer to the method as 'Constitutional AI'. The process involves both a supervised learning and a reinforcement learning phase. In the supervised phase we sample from an initial model, then generate self-critiques and revisions, and then finetune the original model on revised responses. In the RL phase, we sample from the finetuned model, use a model to evaluate which of the two samples is better, and then train a preference model from this dataset of AI preferences. We then train with RL using the preference model as the reward signal, i.e. we use 'RL from AI Feedback' (RLAIF). As a result we are able to train a harmless but non-evasive AI assistant that engages with harmful queries by explaining its objections to them. Both the SL and RL methods can leverage chain-of-thought style reasoning to improve the human-judged performance and transparency of AI decision making. These methods make it possible to control AI behavior more precisely and with far fewer human labels.

The findable, accessible, interoperable, and reusable (FAIR) data principles have provided a framework for examining, evaluating, and improving how we share data with the aim of facilitating scientific discovery. Efforts have been made to generalize these principles to research software and other digital products. Artificial intelligence (AI) models -- algorithms that have been trained on data rather than explicitly programmed -- are an important target for this because of the ever-increasing pace with which AI is transforming scientific and engineering domains. In this paper, we propose a practical definition of FAIR principles for AI models and create a FAIR AI project template that promotes adherence to these principles. We demonstrate how to implement these principles using a concrete example from experimental high energy physics: a graph neural network for identifying Higgs bosons decaying to bottom quarks. We study the robustness of these FAIR AI models and their portability across hardware architectures and software frameworks, and report new insights on the interpretability of AI predictions by studying the interplay between FAIR datasets and AI models. Enabled by publishing FAIR AI models, these studies pave the way toward reliable and automated AI-driven scientific discovery.

Vision Transformers (ViTs) have gained significant popularity in recent years and have proliferated into many applications. However, it is not well explored how varied their behavior is under different learning paradigms. We compare ViTs trained through different methods of supervision, and show that they learn a diverse range of behaviors in terms of their attention, representations, and downstream performance. We also discover ViT behaviors that are consistent across supervision, including the emergence of Offset Local Attention Heads. These are self-attention heads that attend to a token adjacent to the current token with a fixed directional offset, a phenomenon that to the best of our knowledge has not been highlighted in any prior work. Our analysis shows that ViTs are highly flexible and learn to process local and global information in different orders depending on their training method. We find that contrastive self-supervised methods learn features that are competitive with explicitly supervised features, and they can even be superior for part-level tasks. We also find that the representations of reconstruction-based models show non-trivial similarity to contrastive self-supervised models. Finally, we show how the "best" layer for a given task varies by both supervision method and task, further demonstrating the differing order of information processing in ViTs.

Deep metric learning (DML) aims to automatically construct task-specific distances or similarities of data, resulting in a low-dimensional representation. Several significant metric-learning methods have been proposed. Nonetheless, no approach guarantees the preservation of the ordinal nature of the original data in a low-dimensional space. Ordinal data are ubiquitous in real-world problems, such as the severity of symptoms in biomedical cases, production quality in manufacturing, rating level in businesses, and aging level in face recognition. This study proposes a novel angular triangle distance (ATD) and ordinal triplet network (OTD) to obtain an accurate and meaningful embedding space representation for ordinal data. The ATD projects the ordinal relation of data in the angular space, whereas the OTD learns its ordinal projection. We also demonstrated that our new distance measure satisfies the distance metric properties mathematically. The proposed method was assessed using real-world data with an ordinal nature, such as biomedical, facial, and hand-gestured images. Extensive experiments have been conducted, and the results show that our proposed method not only semantically preserves the ordinal nature but is also more accurate than existing DML models. Moreover, we also demonstrate that our proposed method outperforms the state-of-the-art ordinal metric learning method.