Canada has been investing in machine learning and artificial intelligence (AI) for longer than most of the industrialized world. Dr. Geoff Hinton of Google helped ignite the field of graphics processing unit (GPU) deep learning at the University of Toronto. Then he became chief scientific advisor to the Vector Institute, which in collaboration with the University, aims to produce the largest number of deep learning AI graduates and innovators globally. It's the home of computer scientist Yoshua Bengio, who is another pioneer of AI technology. Hundreds of AI researchers and doctoral students are concentrated at McGill University and the University of Montreal.

Scientists from the Case Western Reserve University digital imaging lab, already pioneering the use of Artificial Intelligence (AI) to predict whether chemotherapy will be successful, can now determine which lung-cancer patients will benefit from expensive immunotherapy. And, once again, they're doing it by teaching a computer to find previously unseen changes in patterns in CT scans taken when the lung cancer is first diagnosed compared to scans taken after the first 2-3 cycles of immunotherapy treatment. And, as with previous work, those changes have been discovered both inside -- and outside -- the tumor, a signature of the lab's recent research. "This is no flash in the pan -- this research really seems to be reflecting something about the very biology of the disease, about which is the more aggressive phenotype, and that's information oncologists do not currently have," said Anant Madabhushi, whose Center for Computational Imaging and Personalized Diagnostics (CCIPD) has become a global leader in the detection, diagnosis and characterization of various cancers and other diseases by meshing medical imaging, machine learning and AI. Currently, only about 20% of all cancer patients will actually benefit from immunotherapy, a treatment that differs from chemotherapy in that it uses drugs to help your immune system fight cancer, while chemotherapy uses drugs to directly kill cancer cells, according to the National Cancer Institute.

Are you sure you want to view these Tweets? Learn why emerging #technologies are creating new mobility opportunities to improve the customer experience. How informed are #insurance #customers when it comes to knowing what products are right for them? As #customer expectations #rapidly evolve, travel brands must transform the #innovation #agenda at the same pace, or risk falling far behind.https://lnkd.in/fajXdRm Prioritizing certain specific #interdependences between 5 key roles of a #CEO highlight differences between a good #performer and a #great one..https://lnkd.in/fDTaJ5Y

Neural networks with redundant representation: detecting the undetectable Elena Agliari, 1, Francesco Alemanno, 2, 3 Adriano Barra, 2, 4 Martino Centonze, 2 and Alberto Fachechi 2, 4 1 Dipartimento di Matematica "Guido Castelnuovo", Sapienza Università di Roma, Roma, Italy 2 Dipartimento di Matematica e Fisica "Ennio De Giorgi", Università del Salento, Lecce, Italy 3 C.N.R. Nanotec, Lecce, Italy 4 Istituto Nazionale di Fisica Nucleare, Sezione di Lecce, Italy (Dated: December 2, 2019) We consider a three-layer Sejnowski machine and show that features learnt via contrastive divergence have a dual representation as patterns in a dense associative memory of order P 4 . The latter is known to be able to Hebbian-store an amount of patterns scaling as N P 1, where N denotes the number of constituting binary neurons interacting P -wisely. We also prove that, by keeping the dense associative network far from the saturation regime (namely, allowing for a number of patterns scaling only linearly with N, while P 2) such a system is able to perform pattern recognition far below the standard signal-to-noise threshold. In particular, a network with P 4 is able to retrieve information whose intensity is O (1) even in the presence of a noise O ( N) in the large N limit. This striking skill stems from a redundancy representation of patterns - which is afforded given the (relatively) low-load information storage - and it contributes to explain the impressive abilities in pattern recognition exhibited by new-generation neural networks. The whole theory is developed rigorously, at the replica symmetric level of approximation, and corroborated by signal-to-noise analysis and Monte Carlo simulations. Artificial intelligence is nearly everywhere in today's society and has rapidly changed the face of economy, communication and science.

We propose a new type of variational autoencoder to perform improved pre-processing for clustering and anomaly detection on data with a given label. Anomalies however are not known or labeled. We call our method conditional latent space variational autonencoder since it separates the latent space by conditioning on information within the data. The method fits one prior distribution to each class in the dataset, effectively expanding the prior distribution to include a Gaussian mixture model. Our approach is compared against the capabilities of a typical variational autoencoder by measuring their V-score during cluster formation with respect to the k-means and EM algorithms. For anomaly detection, we use a new metric composed of the mass-volume and excess-mass curves which can work in an unsupervised setting. We compare the results between established methods such as as isolation forest, local outlier factor and one-class support vector machine.

The performance of financial market prediction systems depends heavily on the quality of features it is using. While researchers have used various techniques for enhancing the stock specific features, less attention has been paid to extracting features that represent general mechanism of financial markets. In this paper, we investigate the importance of extracting such general features in stock market prediction domain and show how it can improve the performance of financial market prediction. We present a framework called U-CNNpred, that uses a CNN-based structure. A base model is trained in a specially designed layer-wise training procedure over a pool of historical data from many financial markets, in order to extract the common patterns from different markets. Our experiments, in which we have used hundreds of stocks in S\&P 500 as well as 14 famous indices around the world, show that this model can outperform baseline algorithms when predicting the directional movement of the markets for which it has been trained for. We also show that the base model can be fine-tuned for predicting new markets and achieve a better performance compared to the state of the art baseline algorithms that focus on constructing market-specific models from scratch.

--V ehicle trajectory prediction is crucial for autonomous driving and advanced driver assistant systems. While existing approaches may sample from a predicted distribution of vehicle trajectories, they lack the ability to explore it - a key ability for evaluating safety from a planning and verification perspective. In this work, we devise a novel approach for generating realistic and diverse vehicle trajectories. We extend the generative adversarial network (GAN) framework with a low-dimensional approximate semantic space, and shape that space to capture semantics such as merging and turning. We sample from this space in a way that mimics the predicted distribution, but allows us to control coverage of semantically distinct outcomes. We validate our approach on a publicly available dataset and show results that achieve state of the art prediction performance, while providing improved coverage of the space of predicted trajectory semantics. V ehicle trajectory prediction is crucial for autonomous driving and advanced driver assistant systems. While existing literature relates to improving the accuracy of prediction [1]-[5], the diversity of the predicted trajectories [6], [7] must be explored.

Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in meaningful objects in input. Sometimes, such networks are trained using data augmentation to encode this invariance into the parameters, which restricts the capacity of the model to learn the content of these objects. A more efficient use of the parameter budget is to encode rotation or translation invariance into the model architecture, which relieves the model from the need to learn them. To enable the model to focus on learning the content of objects other than their locations, we propose to conduct patch ranking of the feature maps before feeding them into the next layer. When patch ranking is combined with convolution and pooling operations, we obtain consistent representations despite the location of meaningful objects in input. We show that the patch ranking module improves the performance of the CNN on many benchmark tasks, including MNIST digit recognition, large-scale image recognition, and image retrieval. The code is available at https://github.com//jasonustc/caffe-multigpu/tree/TICNN .

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with sufficient layers and parameters, hierarchical combinations of convolution (matrix multiplication and non-linear activation) and pooling operations should be able to learn a robust mapping from transformed input images to transform-invariant representations. In this paper, we propose randomly transforming (rotation, scale, and translation) feature maps of CNNs during the training stage. This prevents complex dependencies of specific rotation, scale, and translation levels of training images in CNN models. Rather, each convolutional kernel learns to detect a feature that is generally helpful for producing the transform-invariant answer given the combinatorially large variety of transform levels of its input feature maps. In this way, we do not require any extra training supervision or modification to the optimization process and training images. We show that random transformation provides significant improvements of CNNs on many benchmark tasks, including small-scale image recognition, large-scale image recognition, and image retrieval. The code is available at https://github.com/jasonustc/caffe-multigpu/tree/TICNN.

Through training on unlabeled data, anomaly detection has the potential to impact computer-aided diagnosis by outlining suspicious regions. Previous work on deep-learning-based anomaly detection has primarily focused on the reconstruction error. We argue instead, that pixel-wise anomaly ratings derived from a Variational Autoencoder based score approximation yield a theoretically better grounded and more faithful estimate. In our experiments, Variational Autoencoder gradient-based rating outperforms other approaches on unsupervised pixel-wise tumor detection on the BraTS-2017 dataset with a ROC-AUC of 0.94.