We overview the ensmallen numerical optimization library, which provides a flexible C++ framework for mathematical optimization of user-supplied objective functions. Many types of objective functions are supported, including general, differentiable, separable, constrained, and categorical. A diverse set of pre-built optimizers is provided, including Quasi-Newton optimizers and many variants of Stochastic Gradient Descent. The underlying framework facilitates the implementation of new optimizers. Optimization of an objective function typically requires supplying only one or two C++ functions. Custom behavior can be easily specified via callback functions. Empirical comparisons show that ensmallen outperforms other frameworks while providing more functionality. The library is available at https://ensmallen.org and is distributed under the permissive BSD license.

High computational complexity hinders the widespread usage of neural networks, especially in mobile devices, which are often the basis of fine-grained localization technology for ubiquitous health monitoring, context awareness, and indoor location tracking. In this paper, we present a binarized recurrent neural network whose weight parameters, input, and intermediate hidden layer output signals, are all binary-valued, and require only basic bit logic for the evaluation and training process. The proposed Binarized Long Short-Term Memory Network (B-BLSTM-RNN) is especially suitable for resource-constrained environments since it replaces either floating or fixed-point arithmetic with significantly more efficient bitwise operations. The model is based on a bidirectional Long Short-Term Memory Recurrent Neural Network (BLSTM-RNN). Designed to take contextual information into account, the network can process data gathered from different positions, resulting in a system, that's invariant to transformations and distortions of the input patterns. During the forward pass, the B-BLSTM drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations, which is expected to substantially improve power-efficiency. The binarized network is simple, accurate, efficient, and works on challenging gesture recognition tasks using raw MEM data. To validate the effectiveness of the network we conduct three sets of experiments. We achieved a classification accuracy with a the proposed network of about 90% which only 2% less than the full-precision network. We also compare our method with recent methods and outperform these methods by large margins on the conducted datasets.

Location estimation and navigation, especially on smartphones has shown great progress in the past decade due to its low cost and ability to work without additional infrastructure. However, a challenge is the positioning, both in terms of step detection, step length approximation as well as heading estimation, which must be accurate and robust, even when the use of the device is varied in terms of placement or orientation. In this paper, we propose a scheme for retrieving relevant information to detect steps and to estimate the correct step length from raw inertial measurement unit (IMU) data. This approach uses Bidirectional Long Short-Term Memory Recurrent Neural Networks (BLSTM-RNNs). Designed to take contextual information into account, the network can process data gathered from different positions, resulting in a system, which is invariant with respect to transformation and distortions of the input patterns. An experimental evaluation on a dataset produced from 10 individuals demonstrates that this new approach achieves significant improvements over previous attempts and increase the current state-of-the-art results even in the presence of variations and degradations. We achieved a mean classification rate of 98.5% and a standard deviation of 0.70 for 10000 different test sequences and an average error of 1.45% regarding the step length. Thus is the best result on the task gathered in the experiments compared with competing techniques.