MONTREAL--(BUSINESS WIRE)--Element AI, an artificial intelligence company that delivers groundbreaking AI solutions, today announced it has joined the Partnership on AI (PAI) to design best practices and principles that will promote fairness, safety, transparency, and positive social impact. PAI's goals are to study and formulate best practices on the development, testing, and fielding of AI technologies while advancing the public's understanding of AI. Its mission is to serve as an open platform for discussion and engagement about AI and its influences on people and society as well as identifying and fostering aspirational efforts in AI for socially beneficial purposes. Amazon, Apple, Google/DeepMind, Facebook, IBM and Microsoft founded the partnership to bring different, valuable perspectives to its efforts through the inclusion of innovative companies like Element AI. According to a statement released by the Partnership on AI, "We actively designed the Partnership on AI to bring together a diverse range of voices from for-profit and non-profit, all of whom share our belief in the tenets and are committed to collaboration and open dialogue on the many opportunities and rising challenges around AI." In addition to Element AI, another world renown company to join PAI is Element AI Series A investor NVIDIA along with other prestigious companies including: Accenture, Association for Computer Machinery, AI Now, Amnesty International, Article 19, Berkeley CHAI, doteveryone, Fraunhofer IAO, Future of Life Institute, Hastings Center at Yale University, Hong Kong University Electronic & Computer Engineering, Markkula Center for Applied Ethics, Omidyar Network, Oxford Internet Institute and Tufts HRI Lab.

Clinical measurements collected over time are naturally represented as multivariate time series (MTS), which often contain missing data. An autoencoder can learn low dimensional vectorial representations of MTS that preserve important data characteristics, but cannot deal explicitly with missing data. In this work, we propose a new framework that combines an autoencoder with the Time series Cluster Kernel (TCK), a kernel that accounts for missingness patterns in MTS. Via kernel alignment, we incorporate TCK in the autoencoder to improve the learned representations in presence of missing data. We consider a classification problem of MTS with missing values, representing blood samples of patients with surgical site infection. With our approach, rather than with a standard autoencoder, we learn representations in low dimensions that can be classified better.

A common practice in most of deep convolutional neural architectures is to employ fully-connected layers followed by Softmax activation to minimize cross-entropy loss for the sake of classification. Recent studies show that substitution or addition of the Softmax objective to the cost functions of support vector machines or linear discriminant analysis is highly beneficial to improve the classification performance in hybrid neural networks. We propose a novel paradigm to link the optimization of several hybrid objectives through unified backpropagation. This highly alleviates the burden of extensive boosting for independent objective functions or complex formulation of multiobjective gradients. Hybrid loss functions are linked by basic probability assignment from evidence theory. We conduct our experiments for a variety of scenarios and standard datasets to evaluate the advantage of our proposed unification approach to deliver consistent improvements into the classification performance of deep convolutional neural networks.

Transfer learning is a popular practice in deep neural networks, but fine-tuning of large number of parameters is a hard task due to the complex wiring of neurons between splitting layers and imbalance distributions of data in pretrained and transferred domains. The reconstruction of the original wiring for the target domain is a heavy burden due to the size of interconnections across neurons. We propose a distributed scheme that tunes the convolutional filters individually while backpropagates them jointly by means of basic probability assignment. Some of the most recent advances in evidence theory show that in a vast variety of the imbalanced regimes, optimizing of some proper objective functions derived from contingency matrices prevents biases towards high-prior class distributions. Therefore, the original filters get gradually transferred based on individual contributions to overall performance of the target domain. This largely reduces the expected complexity of transfer learning whilst highly improves precision. Our experiments on standard benchmarks and scenarios confirm the consistent improvement of our distributed deep transfer learning strategy.

The past decade has witnessed a successful application of deep learning to solving many challenging problems in machine learning and artificial intelligence. However, the loss functions of deep neural networks (especially nonlinear networks) are still far from being well understood from a theoretical aspect. In this paper, we enrich the current understanding of the landscape of the square loss functions for three types of neural networks. Specifically, when the parameter matrices are square, we provide an explicit characterization of the global minimizers for linear networks, linear residual networks, and nonlinear networks with one hidden layer. Then, we establish two quadratic types of landscape properties for the square loss of these neural networks, i.e., the gradient dominance condition within the neighborhood of their full rank global minimizers, and the regularity condition along certain directions and within the neighborhood of their global minimizers. These two landscape properties are desirable for the optimization around the global minimizers of the loss function for these neural networks.

In "Dictionary Learning" one tries to recover incoherent matrices $A^* \in \mathbb{R}^{n \times h}$ (typically overcomplete and whose columns are assumed to be normalized) and sparse vectors $x^* \in \mathbb{R}^h$ with a small support of size $h^p$ for some $0

In this paper, we presented a novel convolutional neural network framework for graph modeling, with the introduction of two new modules specially designed for graph-structured data: the $k$-th order convolution operator and the adaptive filtering module. Importantly, our framework of High-order and Adaptive Graph Convolutional Network (HA-GCN) is a general-purposed architecture that fits various applications on both node and graph centrics, as well as graph generative models. We conducted extensive experiments on demonstrating the advantages of our framework. Particularly, our HA-GCN outperforms the state-of-the-art models on node classification and molecule property prediction tasks. It also generates 32% more real molecules on the molecule generation task, both of which will significantly benefit real-world applications such as material design and drug screening.

Motivation: Tumor classification using Imaging Mass Spectrometry (IMS) data has a high potential for future applications in pathology. Due to the complexity and size of the data, automated feature extraction and classification steps are required to fully process the data. Deep learning offers an approach to learn feature extraction and classification combined in a single model. Commonly these steps are handled separately in IMS data analysis, hence deep learning offers an alternative strategy worthwhile to explore. Results: Methodologically, we propose an adapted architecture based on deep convolutional networks to handle the characteristics of mass spectrometry data, as well as a strategy to interpret the learned model in the spectral domain based on a sensitivity analysis. The proposed methods are evaluated on two challenging tumor classification tasks and compared to a baseline approach. Competitiveness of the proposed methods are shown on both tasks by studying the performance via cross-validation. Moreover, the learned models are analyzed by the proposed sensitivity analysis revealing biologically plausible effects as well as confounding factors of the considered task. Thus, this study may serve as a starting point for further development of deep learning approaches in IMS classification tasks.

Similar to convolution neural networks, recurrent neural networks (RNNs) typically suffer from over-parameterization. Quantizing bit-widths of weights and activations results in runtime efficiency on hardware, yet it often comes at the cost of reduced accuracy. This paper proposes a quantization approach that increases model size with bit-width reduction. This approach will allow networks to perform at their baseline accuracy while still maintaining the benefits of reduced precision and overall model size reduction.

Deepmind, the artificial intelligence research organization owned by Google, announced some stunning results Wednesday from research into the next generation of its AlphaGo system: the machines are getting smarter. AlphaGo Zero, the new version of the AlphaGo system that defeated the world's best Go players in competitions over the past few years, was able to teach itself how to play the ancient board game as well as its predecessors in a matter of days with no other input than the basic rules of the game, Deepmind said in a blog post Wednesday. Previous versions of AlphaGo built to compete against human masters of the game required hours and hours of training on Go gameplay, but AlphaGo Zero was able to teach itself to play using a technique called reinforcement learning. Reinforcement learning involves training a system to figure out the best reward outcome from a series of actions, unlike supervised learning, in which the system is taught which outcomes are desired and trained over and over to recognize the factors that lead to those outcomes. Deepmind set up a neural network that played games of Go against itself until it learned how to formulate a winning strategy for a game in which capturing as many stones as possible can be satisfying in early stages, but can lead to big problems as the game plays out.