We consider regret minimization for Adversarial Markov Decision Processes (AMDPs), where the loss functions are changing over time and adversarially chosen, and the learner only observes the losses for the visited state-action pairs (i.e., bandit feedback). While there has been a surge of studies on this problem using Online-Mirror-Descent (OMD) methods, very little is known about the Follow-the-Perturbed-Leader (FTPL) methods, which are usually computationally more efficient and also easier to implement since it only requires solving an offline planning problem. Motivated by this, we take a closer look at FTPL for learning AMDPs, starting from the standard episodic finite-horizon setting. We find some unique and intriguing difficulties in the analysis and propose a workaround to eventually show that FTPL is also able to achieve near-optimal regret bounds in this case. More importantly, we then find two significant applications: First, the analysis of FTPL turns out to be readily generalizable to delayed bandit feedback with order-optimal regret, while OMD methods exhibit extra difficulties (Jin et al., 2022). Second, using FTPL, we also develop the first no-regret algorithm for learning communicating AMDPs in the infinite-horizon setting with bandit feedback and stochastic transitions. Our algorithm is efficient assuming access to an offline planning oracle, while even for the easier full-information setting, the only existing algorithm (Chandrasekaran and Tewari, 2021) is computationally inefficient.

We present Human and Geometric Importance SLAM (HGI-SLAM), a novel approach to loop closure using salient and geometric features. Loop closure is a key element of SLAM, with many established methods for this problem. However, current methods are narrow, using either geometric or salient based features. We merge their successes into a model that outperforms both types of methods alone. Our method utilizes inexpensive monocular cameras and does not depend on depth sensors nor Lidar. HGI-SLAM utilizes geometric and salient features, processes them into descriptors, and optimizes them for a bag of words algorithm. By using a concurrent thread and combing our loop closure detection with ORB-SLAM2, our system is a complete SLAM framework. We present extensive evaluations of HGI loop detection and HGI-SLAM on the KITTI and EuRoC datasets. We also provide a qualitative analysis of our features. Our method runs in real time, and is robust to large viewpoint changes while staying accurate in organic environments. HGI-SLAM is an end-to-end SLAM system that only requires monocular vision and is comparable in performance to state-of-the-art SLAM methods.

Recently, distributed semi-supervised learning (DSSL) algorithms have shown their effectiveness in leveraging unlabeled samples over interconnected networks, where agents cannot share their original data with each other and can only communicate non-sensitive information with their neighbors. However, existing DSSL algorithms cannot cope with data uncertainties and may suffer from high computation and communication overhead problems. To handle these issues, we propose a distributed semi-supervised fuzzy regression (DSFR) model with fuzzy if-then rules and interpolation consistency regularization (ICR). The ICR, which was proposed recently for semi-supervised problem, can force decision boundaries to pass through sparse data areas, thus increasing model robustness. However, its application in distributed scenarios has not been considered yet. In this work, we proposed a distributed Fuzzy C-means (DFCM) method and a distributed interpolation consistency regularization (DICR) built on the well-known alternating direction method of multipliers to respectively locate parameters in antecedent and consequent components of DSFR. Notably, the DSFR model converges very fast since it does not involve back-propagation procedure and is scalable to large-scale datasets benefiting from the utilization of DFCM and DICR. Experiments results on both artificial and real-world datasets show that the proposed DSFR model can achieve much better performance than the state-of-the-art DSSL algorithm in terms of both loss value and computational cost.

Simultaneous localization and mapping (SLAM) frameworks for autonomous navigation rely on robust data association to identify loop closures for back-end trajectory optimization. In the case of autonomous underwater vehicles (AUVs) equipped with multibeam echosounders (MBES), data association is particularly challenging due to the scarcity of identifiable landmarks in the seabed, the large drift in dead-reckoning navigation estimates to which AUVs are prone and the low resolution characteristic of MBES data. Deep learning solutions to loop closure detection have shown excellent performance on data from more structured environments. However, their transfer to the seabed domain is not immediate and efforts to port them are hindered by the lack of bathymetric datasets. Thus, in this paper we propose a neural network architecture aimed to showcase the potential of adapting such techniques to correspondence matching in bathymetric data. We train our framework on real bathymetry from an AUV mission and evaluate its performance on the tasks of loop closure detection and coarse point cloud alignment. Finally, we show its potential against a more traditional method and release both its implementation and the dataset used.

Scientists have decoded visual images from a dog's brain, offering a first look at how the canine mind reconstructs what it sees. The Journal of Visualized Experiments published the research done at Emory University. The results suggest that dogs are more attuned to actions in their environment rather than to who or what is doing the action. The researchers recorded the fMRI neural data for two awake, unrestrained dogs as they watched videos in three 30-minute sessions, for a total of 90 minutes. They then used a machine-learning algorithm to analyze the patterns in the neural data.

As a 42-year-old, newly single mom, I was a little insecure when I joined Match.com to meet a nice guy. I described myself as a feminist law professor, interested in liberal intellectuals within five years, plus or minus, of my age. The people who contacted me only eroded my confidence, however. I got cryptic messages from much older and more conservative high school grads, pictured on their motorcycles. These suitors and I ostensibly had nothing in common.

What do I mean by the Artificial Intelligence (AI) revolution? With all the AI hype, it is worth explaining it again from my point of view. Coined by Stanford University researcher John McCarthy, AI is the ability of a machine or a computer to think and learn – and therefore act in ways that are smart. The broad concept or idea here is to build machines capable of thinking, acting and learning like humans. In the past decade, AI has been cited as one of the transformative technologies that have made big strides in many industries including retail, healthcare, banking and finance, agriculture, manufacturing, travel and entertainment, education, public administration and many more.

Role requiring'No experience data provided' months of experience in None Role requiring'No experience data provided' months of experience in None Events in recent years have made us all too familiar with the havoc that natural disasters can wreak, and the increasing frequency and intensity with which they are occurring. Despite record levels of losses, conventional methods of risk modeling continue to paint at best an incomplete picture of these threats. While AI alone may not be able to thwart these disasters, it can help us become more prepared for them, and ultimately that will lead to better outcomes. As a Senior Data Scientist – Computer Vision, you are comfortable and excited to work closely with the engineering team to build the best AI tech possible. You will scale the development of top-tier models by using diverse data sources to provide strong insights and maximize the impact of our company efforts.

Artificial intelligence and machine learning are critical to the future of organizations. Along the AI/ML journey, there will be disruption before there is innovation and transformation. As Gen Z slowly takes over as the largest percentage of the workforce, IT professionals need to anticipate the skills needed to flourish in the emerging world of artificial intelligence. This blog explores how to prepare the next generation of AI practitioners to surf the wave of incoming disruption. If you had the opportunity to go back in time and become an expert in a technical field before it hits its peak, would you?

We introduce De Bruijn Graph Neural Networks (DBGNNs), a novel time-aware graph neural network architecture for time-resolved data on dynamic graphs. Our approach accounts for temporal-topological patterns that unfold in the causal topology of dynamic graphs, which is determined by causal walks, i.e. temporally ordered sequences of links by which nodes can influence each other over time. Our architecture builds on multiple layers of higher-order De Bruijn graphs, an iterative line graph construction where nodes in a De Bruijn graph of order k represent walks of length k-1, while edges represent walks of length k. We develop a graph neural network architecture that utilizes De Bruijn graphs to implement a message passing scheme that follows a non-Markovian dynamics, which enables us to learn patterns in the causal topology of a dynamic graph. Addressing the issue that De Bruijn graphs with different orders k can be used to model the same data set, we further apply statistical model selection to determine the optimal graph topology to be used for message passing. An evaluation in synthetic and empirical data sets suggests that DBGNNs can leverage temporal patterns in dynamic graphs, which substantially improves the performance in a supervised node classification task.