Low-resolution neural networks represent both weights and activations with few bits, drastically reducing the multiplication complexity. Nonetheless, these products are accumulated using high-resolution (typically 32-bit) additions, an operation that dominates the arithmetic complexity of inference when using extreme quantization (e.g., binary weights). To further optimize inference, we propose a method that adapts neural networks to use low-resolution (8-bit) additions in the accumulators, achieving classification accuracy comparable to their 32-bit counterparts. We achieve resilience to low-resolution accumulation by inserting a cyclic activation layer, as well as an overflow penalty regularizer. We demonstrate the efficacy of our approach on both software and hardware platforms.

Undersampling the k-space in MRI allows saving precious acquisition time, yet results in an ill-posed inversion problem. Recently, many deep learning techniques have been developed, addressing this issue of recovering the fully sampled MR image from the undersampled data. However, these learning based schemes are susceptible to differences between the training data and the image to be reconstructed at test time. One such difference can be attributed to the bias field present in MR images, caused by field inhomogeneities and coil sensitivities. In this work, we address the sensitivity of the reconstruction problem to the bias field and propose to model it explicitly in the reconstruction, in order to decrease this sensitivity. To this end, we use an unsupervised learning based reconstruction algorithm as our basis and combine it with a N4-based bias field estimation method, in a joint optimization scheme. We use the HCP dataset as well as in-house measured images for the evaluations. We show that the proposed method improves the reconstruction quality, both visually and in terms of RMSE.

Wrist accelerometers for assessing hallmark measures of physical activity (PA) are rapidly growing with the advent of smartwatch technology. Given the growing popularity of wrist-worn accelerometers, there needs to be a rigorous evaluation for recognizing (PA) type and estimating energy expenditure (EE) across the lifespan. Participants (66% women, aged 20-89 yrs) performed a battery of 33 daily activities in a standardized laboratory setting while a tri-axial accelerometer collected data from the right wrist. A portable metabolic unit was worn to measure metabolic intensity. We built deep learning networks to extract spatial and temporal representations from the time-series data, and used them to recognize PA type and estimate EE. The deep learning models resulted in high performance; the F1 score was: 0.82, 0.81, and 95 for recognizing sedentary, locomotor, and lifestyle activities, respectively. The root mean square error was 1.1 (+/-0.13) for the estimation of EE.

The click-through rate (CTR) reflects the ratio of clicks on a specific item to its total number of views. It has significant impact on websites' advertising revenue. Learning sophisticated models to understand and predict user behavior is essential for maximizing the CTR in recommendation systems. Recent works have suggested new methods that replace the expensive and time-consuming feature engineering process with a variety of deep learning (DL) classifiers capable of capturing complicated patterns from raw data; these methods have shown significant improvement on the CTR prediction task. While DL techniques can learn intricate user behavior patterns, it relies on a vast amount of data and does not perform as well when there is a limited amount of data. We propose XDBoost, a new DL method for capturing complex patterns that requires just a limited amount of raw data. XDBoost is an iterative three-stage neural network model influenced by the traditional machine learning boosting mechanism. XDBoost's components operate sequentially similar to boosting; However, unlike conventional boosting, XDBoost does not sum the predictions generated by its components. Instead, it utilizes these predictions as new artificial features and enhances CTR prediction by retraining the model using these features. Comprehensive experiments conducted to illustrate the effectiveness of XDBoost on two datasets demonstrated its ability to outperform existing state-of-the-art (SOTA) models for CTR prediction.

When the training and test data are from different distributions, domain adaptation is needed to reduce dataset bias to improve the model's generalization ability. Since it is difficult to directly match the cross-domain joint distributions, existing methods tend to reduce the marginal or conditional distribution divergence using predefined distances such as MMD and adversarial-based discrepancies. However, it remains challenging to determine which method is suitable for a given application since they are built with certain priors or bias. Thus they may fail to uncover the underlying relationship between transferable features and joint distributions. This paper proposes Learning to Match (L2M) to automatically learn the cross-domain distribution matching without relying on hand-crafted priors on the matching loss. Instead, L2M reduces the inductive bias by using a meta-network to learn the distribution matching loss in a data-driven way. L2M is a general framework that unifies task-independent and human-designed matching features. We design a novel optimization algorithm for this challenging objective with self-supervised label propagation. Experiments on public datasets substantiate the superiority of L2M over SOTA methods. Moreover, we apply L2M to transfer from pneumonia to COVID-19 chest X-ray images with remarkable performance. L2M can also be extended in other distribution matching applications where we show in a trial experiment that L2M generates more realistic and sharper MNIST samples.

Accurate diagnosis of Autism Spectrum Disorder (ASD) is essential for its management and rehabilitation. Neuroimaging techniques that are non-invasive are disease markers and may be leveraged to aid ASD diagnosis. Structural and functional neuroimaging techniques provide physicians substantial information about the structure (anatomy and structural connectivity) and function (activity and functional connectivity) of the brain. Due to the intricate structure and function of the brain, diagnosing ASD with neuroimaging data without exploiting artificial intelligence (AI) techniques is extremely challenging. AI techniques comprise traditional machine learning (ML) approaches and deep learning (DL) techniques. Conventional ML methods employ various feature extraction and classification techniques, but in DL, the process of feature extraction and classification is accomplished intelligently and integrally. In this paper, studies conducted with the aid of DL networks to distinguish ASD were investigated. Rehabilitation tools provided by supporting ASD patients utilizing DL networks were also assessed. Finally, we presented important challenges in this automated detection and rehabilitation of ASD.

A variety of screening approaches have been proposed to diagnose epileptic seizures, using Electroencephalography (EEG) and Magnetic Resonance Imaging (MRI) modalities. Artificial intelligence encompasses a variety of areas, and one of its branches is deep learning. Before the rise of deep learning, conventional machine learning algorithms involving feature extraction were performed. This limited their performance to the ability of those handcrafting the features. However, in deep learning, the extraction of features and classification is entirely automated. The advent of these techniques in many areas of medicine such as diagnosis of epileptic seizures, has made significant advances. In this study, a comprehensive overview of the types of deep learning methods exploited to diagnose epileptic seizures from various modalities has been studied. Additionally, hardware implementation and cloud-based works are discussed as they are most suited for applied medicine.

If you had asked me a year or two ago when Artificial General Intelligence (AGI) would be invented, I'd have told you that we were a long way off. Most experts were saying that AGI was decades away, and some were saying it might not happen at all. The consensus is -- was? -- that all the recent progress in AI concerns so-called "narrow AI," meaning systems that can only perform one specific task. An AGI, or a "strong AI," which could perform any task as well as a human being, is a much harder problem. It is so hard that there isn't a clear roadmap for achieving it, and few researchers are openly working on the topic. GPT-3 is the first model to shake that status-quo seriously. GPT-3 is the latest language model from the OpenAI team.

Proteins are essential to the life of cells, carrying out complex tasks and catalyzing chemical reactions. Scientists and engineers have long sought to harness this power by designing artificial proteins that can perform new tasks, like treat disease, capture carbon, or harvest energy, but many of the processes designed to create such proteins are slow and complex, with a high failure rate. In a breakthrough that could have implications across the healthcare, agriculture, and energy sectors, a team lead by researchers in the Pritzker School of Molecular Engineering (PME) at the University of Chicago has developed an artificial intelligence-led process that uses big data to design new proteins. By developing machine-learning models that can review protein information culled from genome databases, the researchers found relatively simple design rules for building artificial proteins. When the team constructed these artificial proteins in the lab, they found that they performed chemistries so well that they rivaled those found in nature.

New research from UK based AI company and research lab DeepMind is enabling AI agents to perceive dynamic real-world environments more like humans do. The work deals with aligning observed entities across time-steps in both fully observable and partially observable environments and is introduced in the paper AlignNet: Unsupervised Entity Alignment. While humans interact with the world we draw on our understanding of the objects or entities in the environment -- which remains coherent even if an object becomes temporarily occluded. AI agents however have typically been trained using only pixel inputs. Although recently developed unsupervised scene segmentation techniques have enabled object-based inputs, these approaches are limited to single frames, and models cannot keep track of how objects segmented at one time-step correspond (or align) to those at a later time-step.