We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph neural network for learning agent and world state representations with a transformer to encode the task context. When evaluated on the challenging Baby Intuitions Benchmark, IRENE achieves new state-of-the-art performance on three out of its five tasks - with up to 48.9% improvement. In contrast to existing methods, IRENE is able to bind preferences to specific agents, to better distinguish between rational and irrational agents, and to better understand the role of blocking obstacles. We also investigate, for the first time, the influence of the training tasks on test performance. Our analyses demonstrate the effectiveness of IRENE in combining prior knowledge gained during training for unseen evaluation tasks.

During the diagnostic process, clinicians leverage multimodal information, such as chief complaints, medical images, and laboratory-test results. Deep-learning models for aiding diagnosis have yet to meet this requirement. Here we report a Transformer-based representation-learning model as a clinical diagnostic aid that processes multimodal input in a unified manner. Rather than learning modality-specific features, the model uses embedding layers to convert images and unstructured and structured text into visual tokens and text tokens, and bidirectional blocks with intramodal and intermodal attention to learn a holistic representation of radiographs, the unstructured chief complaint and clinical history, structured clinical information such as laboratory-test results and patient demographic information. The unified model outperformed an image-only model and non-unified multimodal diagnosis models in the identification of pulmonary diseases (by 12% and 9%, respectively) and in the prediction of adverse clinical outcomes in patients with COVID-19 (by 29% and 7%, respectively). Leveraging unified multimodal Transformer-based models may help streamline triage of patients and facilitate the clinical decision process.

Neural networks have become shockingly good at generating natural-sounding text, on almost any subject. If I were a student, I'd be thrilled--let a chatbot write that five-page paper on Hamlet's indecision!--but if I were a teacher I'd have mixed feelings. On the one hand, the quality of student essays is about to go through the roof. On the other, what's the point of asking anyone to write anything anymore? Luckily for us, thoughtful people long ago anticipated the rise of artificial intelligence and wrestled with some of the thornier issues.

Ensemble methods can deliver surprising performance gains but also bring significantly higher computational costs, e.g., can be up to 2048X in large-scale ensemble tasks. However, we found that the majority of computations in ensemble methods are redundant. For instance, over 77% of samples in CIFAR-100 dataset can be correctly classified with only a single ResNet-18 model, which indicates that only around 23% of the samples need an ensemble of extra models. To this end, we propose an inference efficient ensemble learning method, to simultaneously optimize for effectiveness and efficiency in ensemble learning. More specifically, we regard ensemble of models as a sequential inference process and learn the optimal halting event for inference on a specific sample. At each timestep of the inference process, a common selector judges if the current ensemble has reached ensemble effectiveness and halt further inference, otherwise filters this challenging sample for the subsequent models to conduct more powerful ensemble. Both the base models and common selector are jointly optimized to dynamically adjust ensemble inference for different samples with various hardness, through the novel optimization goals including sequential ensemble boosting and computation saving. The experiments with different backbones on real-world datasets illustrate our method can bring up to 56\% inference cost reduction while maintaining comparable performance to full ensemble, achieving significantly better ensemble utility than other baselines. Code and supplemental materials are available at https://seqml.github.io/irene.

Deep learning models are nowadays broadly deployed to solve an incredibly large variety of tasks. Commonly, leveraging over the availability of "big data", deep neural networks are trained as black-boxes, minimizing an objective function at its output. This however does not allow control over the propagation of some specific features through the model, like gender or race, for solving some an uncorrelated task. This raises issues either in the privacy domain (considering the propagation of unwanted information) and of bias (considering that these features are potentially used to solve the given task). In this work we propose IRENE, a method to achieve information removal at the bottleneck of deep neural networks, which explicitly minimizes the estimated mutual information between the features to be kept ``private'' and the target. Experiments on a synthetic dataset and on CelebA validate the effectiveness of the proposed approach, and open the road towards the development of approaches guaranteeing information removal in deep neural networks.

We often speak about the technology (re)evolution that is driving the intelligent factory and Industry 4.0 –more robots, machines with embedded sensors that send signals to a networked factory, and machines that "talk" to each other and to the larger enterprise system. What we don't often address is the role of the human in this intelligent factory operation. Pundits claim that the intelligent factory will replace workers with machines and will obsolete human intuition and decision-making through artificial intelligence (AI). What these pundits get wrong is that not every job can--or should--be displaced with technology. Instead, we should be thinking about how technology enhances human tasks and performance--which is why we at Intel recently studied over 150 workers from the factory floor to the C-suite, to better understand manufacturing workers' pain points, their beliefs about the future of their operations, and their best guess for future technologies.

Who are the Women in STEM who changed the world through science, technology, engineering and mathematics? We asked this question of women at Ayogo, adding "who are the women in STEM you wish you knew?" Here's our list of 13 amazingly cool women in STEM who we wish we knew. Born in 1918, Katherine Johnson, graduated from university at 18. She was awarded the Presidential Medal of Freedom in 2015 for a lifetime of work as a pioneering physicist, mathematician and space scientist. She and her colleagues, Dorothy Vaughan and Mary Jackson did the calculations that guided NASA's 1962 Friendship 7 Mission.