Think back to what you ate for breakfast this morning. Did you picture yourself in your kitchen and visualize the plate in front of you to remember exactly what you ate? That's called an episodic memory – a memory of a particular event that happened at a specific time and place, as opposed to a semantic memory, which refers to more general knowledge or rules that someone understands. Cognitive scientists have long thought that humans were the only animals capable of traveling down memory lane by having episodic memories. Dogs, for example, were known to commit things to semantic memory. When repeatedly trained to sit, stay, or lie down, they learn a rule. But they, like other nonhuman animals, were thought to live exclusively in the here and now – until now.

Before a classification algorithm can do its magic, we need to train it by showing thousands of examples of cats and backgrounds. Different learning algorithms learn differently, but the general principle is that learning algorithms treat feature vectors as points in higher dimensional space, and try to find planes / surfaces that partition the higher dimensional space in such a way that all examples belonging to the same class are on one side of the plane / surface. To simplify things, let us look at one learning algorithm called Support Vector Machines ( SVM) in some detail. Support Vector Machine ( SVM) is one of the most popular supervised binary classification algorithm. Although the ideas used in SVM have been around since 1963, the current version was proposed in 1995 by Cortes and Vapnik. In the previous step, we learned that the HOG descriptor of an image is a feature vector of length 3780. We can think of this vector as a point in a 3780-dimensional space. Visualizing higher dimensional space is impossible, so let us simplify things a bit and imagine the feature vector was just two dimensional. In our simplified world, we now have 2D points representing the two classes ( e.g.

Your smartphone may soon be able to give you an honest answer, thanks to a new machine learning algorithm designed by engineering researchers at the University of Toronto. The researchers trained their algorithm to identify people's hair in photographs--a much more challenging task for computers than it is for humans. The team designed an algorithm that learns directly from human instructions, rather than an existing set of examples, and outperformed conventional methods of training neural networks by 160 percent. More surprisingly, their algorithm also outperformed its own training by nine percent--it learned to recognize hair in pictures with greater reliability than that enabled by the training, marking a significant leap forward for artificial intelligence. "Our algorithm learned to correctly classify difficult, borderline cases--distinguishing the texture of hair versus the texture of the background," said researcher Parham Aarabi.

SALT LAKE CITY, UT--(Marketwired - Nov 14, 2016) - SC16 -- To help companies join the AI revolution, NVIDIA today announced a collaboration with Microsoft to accelerate AI in the enterprise. Using the first purpose-built enterprise AI framework optimized to run on NVIDIA Tesla GPUs in Microsoft Azure or on-premises, enterprises now have an AI platform that spans from their data center to Microsoft's cloud. "Every industry has awoken to the potential of AI," said Jen-Hsun Huang, founder and chief executive officer, NVIDIA. "We've worked with Microsoft to create a lightning-fast AI platform that is available from on-premises with our DGX-1 supercomputer to the Microsoft Azure cloud. With Microsoft's global reach, every company around the world can now tap the power of AI to transform their business."

Academic scientists devote their lives to research, often toiling away on problems that few people outside their discipline fully understand. Perhaps some are driven by pure curiosity or competition, while others have a personal interest in the topic at hand. For Shirley Pepke, a genomics researcher based in Los Angeles, the urgency to find answers comes from her own instinct for survival. Since 2014, she has been working on a tool capable of tailoring ovarian cancer treatment to each patient using genomics data and a machine learning algorithm. The first subject in this DIY precision medicine project was Pepke herself, who was diagnosed with stage IIIC ovarian cancer in September 2013.

Various active learning methods based on logistic regression have been proposed. In this paper, we investigate seven state-of-the-art strategies, present an extensive benchmark, and provide a better understanding of their underlying characteristics. Experiments are carried out both on 3 synthetic datasets and 43 real-world datasets, providing insights into the behaviour of these active learning methods with respect to classification accuracy and their computational cost.

Automated extraction of concepts from patient clinical records is an essential facilitator of clinical research. For this reason, the 2010 i2b2/VA Natural Language Processing Challenges for Clinical Records introduced a concept extraction task aimed at identifying and classifying concepts into predefined categories (i.e., treatments, tests and problems). State-of-the-art concept extraction approaches heavily rely on handcrafted features and domain-specific resources which are hard to collect and define. For this reason, this paper proposes an alternative, streamlined approach: a recurrent neural network (the bidirectional LSTM with CRF decoding) initialized with general-purpose, off-the-shelf word embeddings. The experimental results achieved on the 2010 i2b2/VA reference corpora using the proposed framework outperform all recent methods and ranks closely to the best submission from the original 2010 i2b2/VA challenge.

The Schatten-$p$ norm ($00$ satisfying $1/p=1/p_1+1/p_2$, there is an equivalence between the Schatten-$p$ norm of one matrix and the Schatten-$p_1$ and the Schatten-$p_2$ norms of its two factor matrices. We further extend the equivalence to multiple factor matrices and show that all the factor norms can be convex and smooth for any $p>0$. In contrast, the original Schatten-$p$ norm for $0

Multivariate Pattern (MVP) classification can map different cognitive states to the brain tasks. One of the main challenges in MVP analysis is validating the generated results across subjects. However, analyzing multi-subject fMRI data requires accurate functional alignments between neuronal activities of different subjects, which can rapidly increase the performance and robustness of the final results. Hyperalignment (HA) is one of the most effective functional alignment methods, which can be mathematically formulated by the Canonical Correlation Analysis (CCA) methods. Since HA mostly uses the unsupervised CCA techniques, its solution may not be optimized for MVP analysis. By incorporating the idea of Local Discriminant Analysis (LDA) into CCA, this paper proposes Local Discriminant Hyperalignment (LDHA) as a novel supervised HA method, which can provide better functional alignment for MVP analysis. Indeed, the locality is defined based on the stimuli categories in the train-set, where the correlation between all stimuli in the same category will be maximized and the correlation between distinct categories of stimuli approaches to near zero. Experimental studies on multi-subject MVP analysis confirm that the LDHA method achieves superior performance to other state-of-the-art HA algorithms.

We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data. Our approach provides a novel technique to classify big data sets using neural network models. We preprocess the data before training the neural network models. We first expand the data using wavelet analysis. We then compress the wavelet coefficients by mapping them onto a new scaled orthonormal coordinate system. Then the data is used to train a neural network model that enables us to classify cancer patients into two different classes of high-risk and low-risk patients. We use the leave-one-out approach to build a neural network model. This neural network model enables us to classify a patient using genomic data as a high-risk or low-risk patient without any information about the survival time of the patient. The results from genomic data analysis are compared with survival time analysis. It is shown that the expansion and compression of data using wavelet analysis and singular value decomposition (SVD) is essential to train the neural network model.