Efficient Unitary Neural Network (EUNN)
Using unitary (instead of general) matrices in artificial neural networks (ANNs) is a promising way to solve the gradient explosion/vanishing problem, as well as to enable ANNs to learn long-term correlations in the data. This approach appears particularly promising for Recurrent Neural Networks (RNNs). In this work, we present a new architecture for implementing an Efficient Unitary Neural Network (EUNNs); its main advantages can be summarized as follows. Firstly, the representation capacity of the unitary space in an EUNN is fully tunable, ranging from a subspace of SU(N) to the entire unitary space. Secondly, the computational complexity for training an EUNN is merely O(1) per parameter. Finally, we test the performance of EUNNs on the standard copying task, the pixel-permuted MNIST digit recognition benchmark as well as the Speech Prediction Test (TIMIT). We find that our architecture significantly outperforms both other state-of-the-art unitary RNNs and the LSTM architecture, in terms of the final performance and/or the wall-clock training speed. EUNNs are thus promising alternatives to RNNs and LSTMs for a wide variety of applications. …

ML.NET
1. Machine Learning made for .NET: ML.NET is a machine learning framework built for .NET developers. Use your .NET and C# or F# skills to easily integrate custom machine learning into your applications without any prior expertise in developing or tuning machine learning models.
2. Open source and cross-platform: ML.NET is open source and runs on Windows, Linux, and macOS. Our public release is still in-development, and we want your help! Join the community and contribute your ideas to help us shape what comes next.
3. Proven and extensible: Use the same framework behind recognized Microsoft features like Windows Hello, Bing Ads, and PowerPoint Design Ideas to power your own applications. We’re building ML.NET as an extensible framework, with support for Light GBM, Accord.NET, CNTK, and TensorFlow coming soon.
4. Cover your developer scenarios: Enhance your .NET apps with sentiment analysis, price prediction, fraud detection, and more using custom models built with ML.NET. …

Laplacian Power Network
Deep Neural Networks often suffer from lack of robustness to adversarial noise. To mitigate this drawback, authors have proposed different approaches, such as adding regularizers or training using adversarial examples. In this paper we propose a new regularizer built upon the Laplacian of similarity graphs obtained from the representation of training data at each intermediate representation. This regularizer penalizes large changes (across consecutive layers in the architecture) in the distance between examples of different classes. We provide theoretical justification for this regularizer and demonstrate its effectiveness when facing adversarial noise on classical supervised learning vision datasets. …