Affordance knowledge is a fundamental aspect of commonsense knowledge. Recent findings indicate that world knowledge emerges through large-scale self-supervised pretraining, motivating our exploration of acquiring affordance knowledge from the visual domain. To this end, we augment an existing instructional video resource to create the new Causal Action-Effect (CAE) dataset and design two novel pretraining tasks -- Masked Action Modeling (MAM) and Masked Effect Modeling (MEM) -- promoting the acquisition of two affordance properties in models: behavior and entity equivalence, respectively. We empirically demonstrate the effectiveness of our proposed methods in learning affordance properties. Furthermore, we show that a model pretrained on both tasks outperforms a strong image-based visual-linguistic foundation model (FLAVA) as well as pure linguistic models on a zero-shot physical reasoning probing task.

In many real-world applications, from robotics to pedestrian trajectory prediction, there is a need to predict multiple real-valued outputs to represent several potential scenarios. Current deep learning techniques to address multiple-output problems are based on two main methodologies: (1) mixture density networks, which suffer from poor stability at high dimensions, or (2) multiple choice learning (MCL), an approach that uses $M$ single-output functions, each only producing a point estimate hypothesis. This paper presents a Mixture of Multiple-Output functions (MoM) approach using a novel variant of dropout, Multiple Hypothesis Dropout. Unlike traditional MCL-based approaches, each multiple-output function not only estimates the mean but also the variance for its hypothesis. This is achieved through a novel stochastic winner-take-all loss which allows each multiple-output function to estimate variance through the spread of its subnetwork predictions. Experiments on supervised learning problems illustrate that our approach outperforms existing solutions for reconstructing multimodal output distributions. Additional studies on unsupervised learning problems show that estimating the parameters of latent posterior distributions within a discrete autoencoder significantly improves codebook efficiency, sample quality, precision and recall.

Logical reasoning is central to complex human activities, such as thinking, debating, and planning; it is also a central component of many AI systems as well. In this paper, we investigate the extent to which encoder-only transformer language models (LMs) can reason according to logical rules. We ask whether those LMs can deduce theorems in propositional calculus and first-order logic; if their relative success in these problems reflects general logical capabilities; and which layers contribute the most to the task. First, we show for several encoder-only LMs that they can be trained, to a reasonable degree, to determine logical validity on various datasets. Next, by cross-probing fine-tuned models on these datasets, we show that LMs have difficulty in transferring their putative logical reasoning ability, which suggests that they may have learned dataset-specific features, instead of a general capability. Finally, we conduct a layerwise probing experiment, which shows that the hypothesis classification task is mostly solved through higher layers.

omputer vision is used in this work to detect lighting elements in buildings with the goal of improving the accuracy of previous methods to provide a precise inventory of the location and state of lamps. Using the framework developed in our previous works, we introduce two new modifications to enhance the system: first, a constraint on the orientation of the detected poses in the optimization methods for both the initial and the refined estimates based on the geometric information of the building information modelling (BIM) model; second, an additional reprojection error filtering step to discard the erroneous poses introduced with the orientation restrictions, keeping the identification and localization errors low while greatly increasing the number of detections. These enhancements are tested in five different case studies with more than 30,000 images, with results showing improvements in the number of detections, the percentage of correct model and state identifications, and the distance between detections and reference positions.omputer Using the framework developed in our previous works, we introduce two new modifications to enhance the system: first, a constraint on the orientation of the detected poses in the optimization methods for both the initial and the refined estimates based on the geometric information of the building information modelling (BIM) model; second, an additional reprojection error filtering step to discard the erroneous poses introduced with the orientation restrictions, keeping the identification and localization errors low while greatly increasing the number of detections. These enhancements are tested in five different case studies with more than 30,000 images, with results showing improvements in the number of detections, the percentage of correct model and state identifications, and the distance between detections and reference positions.C Index Terms building lighting, lamp detection, pose estimation, building information modelling Lighting is one of the most important aspects in the design, cost and maintenance of a building. Approximately, one-third of the electricity consumed in buildings corresponds to artificial lighting [1, 2, 3], with a global demand that represents 19% of all the electricity used in the world [4].

Retrieval-augmented generation (RAG) grounds large language model (LLM) output by leveraging external knowledge sources to reduce factual hallucinations. However, prior works lack a comprehensive evaluation of different language families, making it challenging to evaluate LLM robustness against errors in external retrieved knowledge. To overcome this, we establish NoMIRACL, a human-annotated dataset for evaluating LLM robustness in RAG across 18 typologically diverse languages. NoMIRACL includes both a non-relevant and a relevant subset. Queries in the non-relevant subset contain passages manually judged as non-relevant or noisy, whereas queries in the relevant subset include at least a single judged relevant passage. We measure LLM robustness using two metrics: (i) hallucination rate, measuring model tendency to hallucinate an answer, when the answer is not present in passages in the non-relevant subset, and (ii) error rate, measuring model inaccuracy to recognize relevant passages in the relevant subset. We build a GPT-4 baseline which achieves a 33.2% hallucination rate on the non-relevant and a 14.9% error rate on the relevant subset on average. Our evaluation reveals that GPT-4 hallucinates frequently in high-resource languages, such as French or English. This work highlights an important avenue for future research to improve LLM robustness to learn how to better reject non-relevant information in RAG.

Sentence and word embeddings encode structural and semantic information in a distributed manner. Part of the information encoded -- particularly lexical information -- can be seen as continuous, whereas other -- like structural information -- is most often discrete. We explore whether we can compress transformer-based sentence embeddings into a representation that separates different linguistic signals -- in particular, information relevant to subject-verb agreement and verb alternations. We show that by compressing an input sequence that shares a targeted phenomenon into the latent layer of a variational autoencoder-like system, the targeted linguistic information becomes more explicit. A latent layer with both discrete and continuous components captures better the targeted phenomena than a latent layer with only discrete or only continuous components. These experiments are a step towards separating linguistic signals from distributed text embeddings and linking them to more symbolic representations.

Novelty adaptation is the ability of an intelligent agent to adjust its behavior in response to changes in its environment. This is an important characteristic of intelligent agents, as it allows them to continue to function effectively in novel or unexpected situations, but still stands as a critical challenge for deep reinforcement learning (DRL). To tackle this challenge, we propose a simple yet effective novel method, NAPPING (Novelty Adaptation Principles Learning), that allows trained DRL agents to respond to different classes of novelties in open worlds rapidly. With NAPPING, DRL agents can learn to adjust the trained policy only when necessary. They can quickly generalize to similar novel situations without affecting the part of the trained policy that still works. To demonstrate the efficiency and efficacy of NAPPING, we evaluate our method on four action domains that are different in reward structures and the type of task. The domains are CartPole and MountainCar (classic control), CrossRoad (path-finding), and AngryBirds (physical reasoning). We compare NAPPING with standard online and fine-tuning DRL methods in CartPole, MountainCar and CrossRoad, and state-of-the-art methods in the more complicated AngryBirds domain. Our evaluation results demonstrate that with our proposed method, DRL agents can rapidly and effectively adjust to a wide range of novel situations across all tested domains.

Financial literacy (FL) represents a person's ability to turn assets into income, and understanding digital currencies has been added to the modern definition. FL can be predicted by exploiting unlabelled recorded data in financial networks via semi-supervised learning (SSL). Measuring and predicting FL has not been widely studied, resulting in limited understanding of customer financial engagement consequences. Previous studies have shown that low FL increases the risk of social harm. Therefore, it is important to accurately estimate FL to allocate specific intervention programs to less financially literate groups. This will not only increase company profitability, but will also reduce government spending. Some studies considered predicting FL in classification tasks, whereas others developed FL definitions and impacts. The current paper investigated mechanisms to learn customer FL level from their financial data using sampling by synthetic minority over-sampling techniques for regression with Gaussian noise (SMOGN). We propose the SMOGN-COREG model for semi-supervised regression, applying SMOGN to deal with unbalanced datasets and a nonparametric multi-learner co-regression (COREG) algorithm for labeling. We compared the SMOGN-COREG model with six well-known regressors on five datasets to evaluate the proposed models effectiveness on unbalanced and unlabelled financial data. Experimental results confirmed that the proposed method outperformed the comparator models for unbalanced and unlabelled financial data. Therefore, SMOGN-COREG is a step towards using unlabelled data to estimate FL level.

Speech Emotion Recognition (SER) affective technology enables the intelligent embedded devices to interact with sensitivity. Similarly, call centre employees recognise customers' emotions from their pitch, energy, and tone of voice so as to modify their speech for a high-quality interaction with customers. This work explores, for the first time, the effects of the harmonic and percussive components of Mel spectrograms in SER. We attempt to leverage the Mel spectrogram by decomposing distinguishable acoustic features for exploitation in our proposed architecture, which includes a novel feature map generator algorithm, a CNN-based network feature extractor and a multi-layer perceptron (MLP) classifier. This study specifically focuses on effective data augmentation techniques for building an enriched hybrid-based feature map. This process results in a function that outputs a 2D image so that it can be used as input data for a pre-trained CNN-VGG16 feature extractor. Furthermore, we also investigate other acoustic features such as MFCCs, chromagram, spectral contrast, and the tonnetz to assess our proposed framework. A test accuracy of 92.79% on the Berlin EMO-DB database is achieved. Our result is higher than previous works using CNN-VGG16.

Emotion recognition (ER) from speech signals is a robust approach since it cannot be imitated like facial expression or text based sentiment analysis. Valuable information underlying the emotions are significant for human-computer interactions enabling intelligent machines to interact with sensitivity in the real world. Previous ER studies through speech signal processing have focused exclusively on associations between different signal mode decomposition methods and hidden informative features. However, improper decomposition parameter selections lead to informative signal component losses due to mode duplicating and mixing. In contrast, the current study proposes VGG-optiVMD, an empowered variational mode decomposition algorithm, to distinguish meaningful speech features and automatically select the number of decomposed modes and optimum balancing parameter for the data fidelity constraint by assessing their effects on the VGG16 flattening output layer. Various feature vectors were employed to train the VGG16 network on different databases and assess VGG-optiVMD reproducibility and reliability. One, two, and three-dimensional feature vectors were constructed by concatenating Mel-frequency cepstral coefficients, Chromagram, Mel spectrograms, Tonnetz diagrams, and spectral centroids. Results confirmed a synergistic relationship between the fine-tuning of the signal sample rate and decomposition parameters with classification accuracy, achieving state-of-the-art 96.09% accuracy in predicting seven emotions on the Berlin EMO-DB database.