Electroencephalogram (EEG) signal is widely used in brain computer interfaces (BCI), the pattern of which differs significantly across different subjects, and poses a major challenge for real world application of EEG classifiers. We found an efficient transfer learning method, named Meta UPdate Strategy (MUPS), boosts cross subject classification performance of EEG signals, and only need a small amount of data from target subject. The model tackles the problem with a two step process: (1) extract versatile features that are effective across all source subjects, and (2) adapt the model to target subject. The proposed model, which originates from meta learning, aims to find feature representation that is broadly suitable for different subjects, and maximizes sensitivity of the loss function on new subject such that one or a small number of gradient steps can lead to effective adaptation. The method can be applied to all deep learning oriented models. We performed extensive experiments on two public datasets, the proposed MUPS model outperforms current state of the arts by a large margin on accuracy and AUC-ROC when only a small amount of target data is used.

Semi-supervised graph embedding methods represented by graph convolutional network has become one of the most popular methods for utilizing deep learning approaches to process the graph-based data for applications. Mostly existing work focus on designing novel algorithm structure to improve the performance, but ignore one common training problem, i.e., could these methods achieve the same performance with limited labelled data? To tackle this research gap, we propose a sampling-based training framework for semi-supervised graph embedding methods to achieve better performance with smaller training data set. The key idea is to integrate the sampling theory and embedding methods by a pipeline form, which has the following advantages: 1) the sampled training data can maintain more accurate graph characteristics than uniformly chosen data, which eliminates the model deviation; 2) the smaller scale of training data is beneficial to reduce the human resource cost to label them; The extensive experiments show that the sampling-based method can achieve the same performance only with 10$\%$-50$\%$ of the scale of training data. It verifies that the framework could extend the existing semi-supervised methods to the scenarios with the extremely small scale of labelled data.

We propose a Bayesian physics-informed neural network (B-PINN) to solve both forward and inverse nonlinear problems described by partial differential equations (PDEs) and noisy data. In this Bayesian framework, the Bayesian neural network (BNN) combined with a PINN for PDEs serves as the prior while the Hamiltonian Monte Carlo (HMC) or the variational inference (VI) could serve as an estimator of the posterior. B-PINNs make use of both physical laws and scattered noisy measurements to provide predictions and quantify the aleatoric uncertainty arising from the noisy data in the Bayesian framework. Compared with PINNs, in addition to uncertainty quantification, B-PINNs obtain more accurate predictions in scenarios with large noise due to their capability of avoiding overfitting. We conduct a systematic comparison between the two different approaches for the B-PINN posterior estimation (i.e., HMC or VI), along with dropout used for quantifying uncertainty in deep neural networks. Our experiments show that HMC is more suitable than VI for the B-PINNs posterior estimation, while dropout employed in PINNs can hardly provide accurate predictions with reasonable uncertainty. Finally, we replace the BNN in the prior with a truncated Karhunen-Lo\`eve (KL) expansion combined with HMC or a deep normalizing flow (DNF) model as posterior estimators. The KL is as accurate as BNN and much faster but this framework cannot be easily extended to high-dimensional problems unlike the BNN based framework.

This Letter presents a neural estimator for entropy production, or NEEP, that estimates entropy production (EP) from trajectories without any prior knowledge of the system. For steady state, we rigorously prove that the estimator, which can be built up from different choices of deep neural networks, provides stochastic EP by optimizing the objective function proposed here. We verify the NEEP with the stochastic processes of the bead-spring and discrete flashing ratchet models, and also demonstrate that our method is applicable to high-dimensional data and non-Markovian systems.

Language recognition has been significantly advanced in recent years by means of modern machine learning methods such as deep learning and benchmarks with rich annotations. However, research is still limited in low-resource formal languages. This consists of a significant gap in describing the colloquial language especially for low-resourced ones such as Persian. In order to target this gap for low resource languages, we propose a "Large Scale Colloquial Persian Dataset" (LSCP). LSCP is hierarchically organized in a semantic taxonomy that focuses on multi-task informal Persian language understanding as a comprehensive problem. This encompasses the recognition of multiple semantic aspects in the human-level sentences, which naturally captures from the real-world sentences. We believe that further investigations and processing, as well as the application of novel algorithms and methods, can strengthen enriching computerized understanding and processing of low resource languages. The proposed corpus consists of 120M sentences resulted from 27M tweets annotated with parsing tree, part-of-speech tags, sentiment polarity and translation in five different languages.

A key capability required by service robots operating in real-world, dynamic environments is that of Visual Intelligence, i.e., the ability to use their vision system, reasoning components and background knowledge to make sense of their environment. In this paper, we analyze the epistemic requirements for Visual Intelligence, both in a top-down fashion, using existing frameworks for human-like Visual Intelligence in the literature, and from the bottom up, based on the errors emerging from object recognition trials in a real-world robotic scenario. Finally, we use these requirements to evaluate current knowledge bases for Service Robotics and to identify gaps in the support they provide for Visual Intelligence. These gaps provide the basis of a research agenda for developing more effective knowledge representations for Visual Intelligence.

Agile satellites with advanced attitude maneuvering capability are the new generation of Earth observation satellites (EOSs). The continuous improvement in satellite technology and decrease in launch cost have boosted the development of agile EOSs (AEOSs). To efficiently employ the increasing orbiting AEOSs, the AEOS scheduling problem (AEOSSP) aiming to maximize the entire observation profit while satisfying all complex operational constraints, has received much attention over the past 20 years. The objectives of this paper are thus to summarize current research on AEOSSP, identify main accomplishments and highlight potential future research directions. To this end, general definitions of AEOSSP with operational constraints are described initially, followed by its three typical variations including different definitions of observation profit, multi-objective function and autonomous model. A detailed literature review from 1997 up to 2019 is then presented in line with four different solution methods, i.e., exact method, heuristic, metaheuristic and machine learning. Finally, we discuss a number of topics worth pursuing in the future.

Learning-based approaches often outperform hand-coded algorithmic solutions for many problems in robotics. However, learning long-horizon tasks on real robot hardware can be intractable, and transferring a learned policy from simulation to reality is still extremely challenging. We present a novel approach to model-free reinforcement learning that can leverage existing sub-optimal solutions as an algorithmic prior during training and deployment. During training, our gated fusion approach enables the prior to guide the initial stages of exploration, increasing sample-efficiency and enabling learning from sparse long-horizon reward signals. Importantly, the policy can learn to improve beyond the performance of the sub-optimal prior since the prior's influence is annealed gradually. During deployment, the policy's uncertainty provides a reliable strategy for transferring a simulation-trained policy to the real world by falling back to the prior controller in uncertain states. We show the efficacy of our Multiplicative Controller Fusion approach on the task of robot navigation and demonstrate safe transfer from simulation to the real world without any fine tuning. The code for this project is made publicly available at https://sites.google.com/view/mcf-nav/home.

Artificial intelligence (AI) systems, powered by massive data and sophisticated algorithms -- including but not limited to -- deep neural networks and statistical machine learning (ML)(support vector machines, clustering, random forest, etc.), are having profound and transformative impact on our daily lives as they make their way into everything from finance to healthcare, from retail to transportation. Netflix movie recommender, Amazon's product prediction, Facebook's uncanny ability to show what you may like, Google's assistant, DeepMind's AlphaGo, Stanford's AI beating human doctors. Machine learning is eating software. However, one of the common features of these powerful algorithms is that they utilize sophisticated mathematics to do their job -- to classify and segment an image, to arrive at the key decisions, to make a product recommendation, to model a complex phenomenon, or to extract and visualize a hidden pattern from a deluge of data. All of these mathematical processes are, quite simply, beyond the scope of a single human (or a team) to perform manually (even on a computer) or inside their head.

Arguably more famous today than Michael Bay's Transformers, the transformer architecture and transformer-based models have been breaking all kinds of state-of-the-art records. They are (rightfully) getting the attention of a big portion of the deep learning community and researchers in Natural Language Processing (NLP) since their introduction in 2017 by the Google Translation Team. This architecture has set the stage for today's heavy-weight models: Google AI's BERT (and its variants) have been sitting in first position across many NLP leaderboards. OpenAI's GPT2 was judged so powerful by its authors, that up until recently only a weaker version of it was publicly released, following expressed concerns that this model might be used for "evil"! In this blogpost series, we will walk you through the rise of the transformer architecture.