Magnetic Resonance Imaging (MRI) of the brain can come in the form of different modalities such as T1-weighted and Fluid Attenuated Inversion Recovery (FLAIR) which has been used to investigate a wide range of neurological disorders. Current state-of-the-art models for brain tissue segmentation and disease classification require multiple modalities for training and inference. However, the acquisition of all of these modalities are expensive, time-consuming, inconvenient and the required modalities are often not available. As a result, these datasets contain large amounts of \emph{unpaired} data, where examples in the dataset do not contain all modalities. On the other hand, there is smaller fraction of examples that contain all modalities (\emph{paired} data) and furthermore each modality is high dimensional when compared to number of datapoints. In this work, we develop a method to address these issues with semi-supervised learning in translating between two neuroimaging modalities. Our proposed model, Semi-Supervised Adversarial CycleGAN (SSA-CGAN), uses an adversarial loss to learn from \emph{unpaired} data points, cycle loss to enforce consistent reconstructions of the mappings and another adversarial loss to take advantage of \emph{paired} data points. Our experiments demonstrate that our proposed framework produces an improvement in reconstruction error and reduced variance for the pairwise translation of multiple modalities and is more robust to thermal noise when compared to existing methods.

Most of the data-driven approaches applied to bearing fault diagnosis up to date are established in the supervised learning paradigm, which usually requires a large set of labeled data collected a priori. In practical applications, however, obtaining accurate labels based on real-time bearing conditions can be far more challenging than simply collecting a huge amount of unlabeled data using various sensors. In this paper, we thus propose a semi-supervised learning approach for bearing anomaly detection using variational autoencoder (VAE) based deep generative models, which allows for effective utilization of dataset when only a small subset of data have labels. Finally, a series of experiments is performed using both the Case Western Reserve University (CWRU) bearing dataset and the University of Cincinnati's Center for Intelligent Maintenance Systems (IMS) dataset. The experimental results demonstrate that the proposed semi-supervised learning scheme greatly outperforms two mainstream semi-supervised learning approaches and a baseline supervised convolutional neural network approach, with the overall accuracy improvement ranging between 3% to 30% using different proportions of labeled samples.

Cheetah uses supervised learning techniques to catch its prey. That's a bizarre, random out-of-the-blue statement you may say. A cheetah has adapted a very refined approach to hunting by honing its skills through practice, observation, experience, and computation. Much like training datasets to create a spectacular AI model. They're trained and taught continuously until they're able to operate on their own.

Trees have long been a subject of interest and a topic of discussion -- and it's no wonder; they represent life, growth, peace, and nature. Trees provide us with many benefits necessary for survival, including clean air, filtered water, shade, and food. They also give us hope and insight, and courage to persevere -- even in the harshest conditions. Trees teach us to stay rooted while soaring to great heights. As we know the tree has been useful to us in many different forms, but in the recent times, its structure has given us inspiration for an algorithm to solve problems and make a machine learn things we want them to learn.

Unsupervised learning helps to find a hidden jewel in data by grouping similar things together. Data have no target attribute. The algorithm takes training examples as the set of attributes/features alone. In this post, I have summarised my whole upcoming book "Unsupervised Learning – The Unlabelled Data Treasure" on one page. This one-page guide is to know everything about unsupervised learning on a high level.

Humans and animals solve a difficult problem much more easily when they are presented with a sequence of problems that starts simple and slowly increases in difficulty. We explore this idea in the context of reinforcement learning. Rather than providing the agent with an externally provided curriculum of progressively more difficult tasks, the agent solves a single task utilizing a decreasingly constrained policy space. The algorithm we propose first learns to categorize features into positive and negative before gradually learning a more refined policy. Experimental results in Tetris demonstrate superior learning rate of our approach when compared to existing algorithms.

Amazon Web Services unveiled new EC2 Arm-based instances powered by its AWS-designed Graviton2 processors, along with Inf1 machine-learning inference instances powered by its custom AWS Inferentia chips. "If you look at instances to start, it's not just that we have meaningfully more instances than anybody else, but it's also that we've got a lot more powerful capabilities in each of those instances," AWS CEO Andy Jassy said in his keynote address at the AWS re:Invent 2019 conference in Las Vegas. AWS' pace of innovation has resulted in a significant increase in instances, Jassy said, and AWS now has four times more types today than two years ago. "We have the most powerful GPU machine-learning training instances, most powerful GPU graphics rendering instances, the largest in-memory instances for SAP workflows with 24 terabytes, the fastest processors in the cloud with the z1d," Jassy said. "You've got the only standard instances that have 100 Gigabits per second of network connectivity, the only instances that have all the processor choices from Intel and AMD. A very different set of capabilities on the instances side."

Complex node interactions are common in knowledge graphs, and these interactions also contain rich knowledge information. However, traditional methods usually treat a triple as a training unit during the knowledge representation learning (KRL) procedure, neglecting contextualized information of the nodes in knowledge graphs (KGs). We generalize the modeling object to a very general form, which theoretically supports any subgraph extracted from the knowledge graph, and these subgraphs are fed into a novel transformer-based model to learn the knowledge embeddings. To broaden usage scenarios of knowledge, pre-trained language models are utilized to build a model that incorporates the learned knowledge representations. Experimental results demonstrate that our model achieves the state-of-the-art performance on several medical NLP tasks, and improvement above TransE indicates that our KRL method captures the graph contextualized information effectively.

This paper studies a training method to jointly estimate an energy-based model and a flow-based model, in which the two models are iteratively updated based on a shared adversarial value function. This joint training method has the following traits. (1) The update of the energy-based model is based on noise contrastive estimation, with the flow model serving as a strong noise distribution. (2) The update of the flow model approximately minimizes the Jensen-Shannon divergence between the flow model and the data distribution. (3) Unlike generative adversarial networks (GAN) which estimates an implicit probability distribution defined by a generator model, our method estimates two explicit probabilistic distributions on the data. Using the proposed method we demonstrate a significant improvement on the synthesis quality of the flow model, and show the effectiveness of unsupervised feature learning by the learned energy-based model. Furthermore, the proposed training method can be easily adapted to semi-supervised learning. We achieve competitive results to the state-of-the-art semi-supervised learning methods.

We propose using active learning based techniques to further improve the state-of-the-art semi-supervised learning MixMatch algorithm. We provide a thorough empirical evaluation of several active-learning and baseline methods, which successfully demonstrate a significant improvement on the benchmark CIFAR-10, CIFAR-100, and SVHN datasets (as much as 1.5% in absolute accuracy). We also provide an empirical analysis of the cost trade-off between incrementally gathering more labeled versus unlabeled data. This analysis can be used to measure the relative value of labeled/unlabeled data at different points of the learning curve, where we find that although the incremental value of labeled data can be as much as 20x that of unlabeled, it quickly diminishes to less than 3x once more than 2,000 labeled example are observed. Code can be found at https://github.com/google-research/mma.