There has never been a better time to indulge in the science and technology of Artificial Intelligence. We are a group of people who love what we do. Our founders have a wealth of experience working on various ground-breaking products including self driving cars, AWS AI services, GMail, Google Docs and flash storage systems. Backgrounds include key roles at Google, AWS, Uber, founding team of a startup which had a billion dollar IPO, and degrees from IIT, Stanford and Dartmouth. We are looking for talented backend software engineers, machine learning software engineers and research scientists to be part of the founding team.

This post originally appeared at TheGradient and was edited by Andrey Kurenkov, Eric Wang, and Aditya Ganesh. Big changes are underway in the world of Natural Language Processing (NLP). The long reign of word vectors as NLP's core representation technique has seen an exciting new line of challengers emerge: ELMo[1], ULMFiT[2], and the OpenAI transformer[3]. These works made headlines by demonstrating that pretrained language models can be used to achieve state-of-the-art results on a wide range of NLP tasks. Such methods herald a watershed moment: they may have the same wide-ranging impact on NLP as pretrained ImageNet models had on computer vision. Pretrained word vectors have brought NLP a long way.

Researchers are looking to employ onboard artificial intelligence systems to improve the control and sophistication of prosthetic hands, by using deep learning approaches that read and react to nerve signals transmitted through the arm. The practice of tracking the natural electric impulses sent by the brain to control individual muscles, known as electromyography, has been used to operate prosthetic limbs and hands before, as well as wheelchairs and other devices. But performance gaps remain when it comes to the fine motor control of fingers and hands. By running a neural network in real-time on a dedicated processing unit within the prosthetic, researchers at the University of Texas at Dallas (UT Dallas) hope to speed up responses for faster hand movements. In addition, the proposed system could be retrained based on the actions of the user to increase its accuracy.

Can AI agents learn to generalize beyond its immediate experience? In a study conducted in collaboration with Stanford and the University College London, DeepMind scientists investigated whether systems could apply the knowledge they'd learned in one task to other, tangentially related tasks. They report that in environments ranging from a grid-world to an interactive 3D room generated in Unity (a game engine), their AI-driven agents correctly exploited the "compositional nature" of a language to interpret never-seen-before instructions. "[While] AI systems trained in idealized or reduced situations may fail to exhibit a compositional or systematic understanding of their experience, this competence can readily emerge when, like human learners, they have access to many examples of richly varying, multi-modal observations as they learn," wrote the contributing scientists in a preprint paper summarizing the research. "This suggests that, during training, the agent learns not only how to follow training instructions, but also general information about how word-like symbols compose and how the combination of those words affects what the agent should do in its world."

A recent paper on Capsules has many important insights for revolutionizing learning in Deep Neural Networks. Here is a picture of CapsNet, the neural network architecture using Capsules. The interesting dynamic routing occurs between PrimaryCaps and DigitCaps. Dynamic routing is implemented with two main transformation as reported in these equations (2 in paper). U are the outputs of Capsules in the layer below, and S are outputs from Capsules on layer above.

A recent paper on Capsules has many important insights for revolutionizing learning in Deep Neural Networks. Here is a picture of CapsNet, the neural network architecture using Capsules. The interesting dynamic routing occurs between PrimaryCaps and DigitCaps. Dynamic routing is implemented with two main transformation as reported in these equations (2 in paper). U are the outputs of Capsules in the layer below, and S are outputs from Capsules on layer above.

To whom correspondence should be addressed. Abstract As proteins with similar structures often have similar funct ions, analysis of protein structures can help predict protein functions and is thus imp ortant. We consider the problem of protein structure classification, which computati onally classifies the structures of proteins into predefined groups. We develop a weighted network that depicts the protein structures, and more importantly, we propose the firs t graphlet-based measure that applies to weighted networks. Further, we develop a de ep neural network (DNN) composed of both convolutional and recurrent layers to use this measure for classification. Put together, our approach shows dramatic improvements in performance over existing graphlet-based approaches on 36 real datasets. E ven comparing with the state-of-the-art approach, it almost halves the classification error. In addition to protein structure networks, our weighted-graphlet measure and DNN cla ssifier can potentially be applied to classification of other weighted networks in computational biology as well as in other domains. Proteins are the building molecules of life, and their diver se functions define the mechanisms of sophisticated organisms [1].

Graph kernels are kernel methods measuring graph similarity and serve as a standard tool for graph classification. However, the use of kernel methods for node classification, which is a related problem to graph representation learning, is still ill-posed and the state-of-the-art methods are heavily based on heuristics. Here, we present a novel theoretical kernel-based framework for node classification that can bridge the gap between these two representation learning problems on graphs. Our approach is motivated by graph kernel methodology but extended to learn the node representations capturing the structural information in a graph. We theoretically show that our formulation is as powerful as any positive semidefinite kernels. To efficiently learn the kernel, we propose a novel mechanism for node feature aggregation and a data-driven similarity metric employed during the training phase. More importantly, our framework is flexible and complementary to other graph-based deep learning models, e.g., Graph Convolutional Networks (GCNs). We empirically evaluate our approach on a number of standard node classification benchmarks, and demonstrate that our model sets the new state of the art.

ICU readmission is associated with longer hospitalization, mortality and adverse outcomes. An early recognition of ICU re-admission can help prevent patients from worse situation and lower treatment cost. As the abundance of Electronics Health Records (EHR), it is popular to design clinical decision tools with machine learning technique manipulating on healthcare large scale data. We designed data-driven predictive models to estimate the risk of ICU readmission. The discharge summary of each hospital admission was carefully represented by natural language processing techniques. Unified Medical Language System (UMLS) was further used to standardize inconsistency of discharge summaries. 5 machine learning classifiers were adopted to construct predictive models. The best configuration yielded a competitive AUC of 0.748. Our work suggests that natural language processing of discharge summaries is capable to send clinicians warning of unplanned 30-day readmission upon discharge.

However, as the development of computer technology, the application of machine learning introduced new ideas for seizure forecasting. Applying machine learning model onto the predication of epileptic seizure co uld help us obtain a better result and there have been plenty of scientists who have been doing such works so that there are sufficient medical data provided for researchers to do training of machine learning models. In our research, we applied traditional machine learning algorithms, such as Linear SVM, Logistic Regression, KNN (K Nearest Neighbors), and Neural Networks, like CNN (Convolutional Neural Networks), RNN (Recurrent Neural Networks), and LSTM (Long Short - Term Memory), for prediction. The emphasi s of our research is to compare the AUC (Area Under the Curve) and accuracy of various models. The research result indicates that machine learning has made epileptic seizure prediction an achievable reality.