Specifying utility functions is a key step towards applying the discrete choice framework for understanding the behaviour processes that govern user choices. However, identifying the utility function specifications that best model and explain the observed choices can be a very challenging and time-consuming task. This paper seeks to help modellers by leveraging the Bayesian framework and the concept of automatic relevance determination (ARD), in order to automatically determine an optimal utility function specification from an exponentially large set of possible specifications in a purely data-driven manner. Based on recent advances in approximate Bayesian inference, a doubly stochastic variational inference is developed, which allows the proposed DCM-ARD model to scale to very large and high-dimensional datasets. Using semi-artificial choice data, the proposed approach is shown to very accurately recover the true utility function specifications that govern the observed choices. Moreover, when applied to real choice data, DCM-ARD is shown to be able discover high quality specifications that can outperform previous ones from the literature according to multiple criteria, thereby demonstrating its practical applicability.

There has been a recent trend in training neural networks to replace data structures that have been crafted by hand, with an aim for faster execution, better accuracy, or greater compression. In this setting, a neural data structure is instantiated by training a network over many epochs of its inputs until convergence. In applications where inputs arrive at high throughput, or are ephemeral, training a network from scratch is not practical. This motivates the need for few-shot neural data structures. In this paper we explore the learning of approximate set membership over a set of data in one-shot via meta-learning. We propose a novel memory architecture, the Neural Bloom Filter, which is able to achieve significant compression gains over classical Bloom Filters and existing memory-augmented neural networks.

In line with last year's forecasts, the AI market continues to grow steadily, and in addition to qualitative improvement in technologies, there is a further expansion of the areas in which Artificial Intelligence is being implemented, including such traditional industries as engineering, mining, and agriculture. The spread of AI is due to the fact that the technology has matured enough while continuing to evolve. Above all, we can expect a significant increase in the production of specialized computer chips. Market leaders like NVIDIA, AMD, ARM, and Qualcomm have already begun manufacturing processors optimized for speech recognition and computer vision. According to the experts, the AI chip market will grow by 30-40% this year, while research company Allied Market Research forecasts that the global market could grow to $91.185 billion by 2025.

The field of artificial intelligence (AI) is growing at a rapid pace, developing algorithms and automated machines that show promise in making the workplace more efficient and less biased. Many of us already interact with artificial intelligence in our daily lives, often without even realizing it--it's responsible for everything from credit score calculators to search engine results to what we see on social media.1 Likewise, organizations have introduced AI into many work processes, especially recruiting and talent-management functions. In many cases, algorithms sort through numerous factors to profile people and make predictions about them. AI hiring and talent-management systems have the potential to move the needle on gender equality in workplaces by using more objective criteria in recruiting and promoting talent.2 But what happens if the algorithm is actually relying on biased input to make predictions?

The energy industry is undergoing a rapid transformation in recent past owing to the enhanced role of renewables and enhanced data-driven models making the value chain smarter. In the context of the primary constituents of this sector comprising of coal, power, renewables, solar energy, oil, and gas, there is a huge role AI can play. The biggest disruption in power in recent times is in the smart grid which is quite flexible in comparison to the traditional grid. AI can be a huge enabler in the form of providing optimal configurations etc to create a really smart and efficient grid. By thorough analysis of data related to losses AI can help prevent transmission and distribution losses.

We propose Cormorant, a rotationally covariant neural network architecture for learning the behavior and properties of complex many-body physical systems. We apply these networks to molecular systems with two goals: learning atomic potential energy surfaces for use in Molecular Dynamics simulations, and learning ground state properties of molecules calculated by Density Functional Theory. Some of the key features of our network are that (a) each neuron explicitly corresponds to a subset of atoms; (b) the activation of each neuron is covariant to rotations, ensuring that overall the network is fully rotationally invariant. Furthermore, the non-linearity in our network is based upon tensor products and the Clebsch-Gordan decomposition, allowing the network to operate entirely in Fourier space. Cormorant significantly outperforms competing algorithms in learning molecular Potential Energy Surfaces from conformational geometries in the MD-17 dataset, and is competitive with other methods at learning geometric, energetic, electronic, and thermodynamic properties of molecules on the GDB-9 dataset.

An attribution method was developed to interpret a recurrent neural network (RNN) trained to predict a child's risk of ICU mortality using multi-modal, time series data in the Electronic Medical Records. By learning a sparse, binary mask that highlights salient features of the input data, critical features determining an individual patient's severity of illness could be identified. The method, called Learned Binary Masks (LBM), demonstrated that the RNN used different feature sets specific to each patient's illness; and further, the features highlighted aligned with clinical intuition of the patient's disease trajectories. LBM was also used to identify the most salient features across the model, analogous to "feature importance" computed in the Random Forest. This measure of the RNN's feature importance was further used to select the 25% most used features for training a second RNN model. Interestingly, but not surprisingly, the second model maintained similar performance to the model trained on all features. LBM is data-agnostic and can be used to interpret the predictions of any differentiable model.

In this paper we propose a new method to assist in labeling data arriving from fast running processes using anomaly detection. A result is the possibility to manually classify data arriving at a high rates to train machine learning models. To circumvent the problem of not having a real ground truth we propose specific metrics for model selection and validation of the results. The use case is taken from the food packaging industry, where processes are affected by regular but short breakdowns causing interruptions in the production process. Fast production rates make it hard for machine operators to identify the source and thus the cause of the breakdown. Self learning assistance systems can help them finding the root cause of the problem and assist the machine operator in applying lasting solutions. These learning systems need to be trained to identify reoccurring problems using data analytics. Training is not easy as the process is too fast to be manually monitored to add specific classifications on the single data points.

In this paper, we develop a convolutional neural network model to predict the mechanical properties of a two-dimensional checkerboard composite quantitatively. The checkerboard composite possesses two phases, one phase is soft and ductile while the other is stiff and brittle. The ground-truth data used in the training process are obtained from finite element analyses under the assumption of plane stress. Monte Carlo simulations and central limit theorem are used to find the size of the dataset needed. Once the training process is completed, the developed model is validated using data unseen during training. The developed neural network model captures the stiffness, strength, and toughness of checkerboard composites with high accuracy. Also, we integrate the developed model with a genetic algorithm (GA) optimizer to identify the optimal microstructural designs. The genetic algorithm optimizer adopted here has several operators, selection, crossover, mutation, and elitism. The optimizer converges to configurations with highly enhanced properties. For the case of the modulus and starting from randomly-initialized generation, the GA optimizer converges to the global maximum which involves no soft elements. Also, the GA optimizers, when used to maximize strength and toughness, tend towards having soft elements in the region next to the crack tip.

Graphs are ideal representations of complex, relational information. Their applications span diverse areas of science and engineering, such as Feynman diagrams in fundamental physics, the structures of molecules in chemistry or transport systems in urban planning. Recently, many of these examples turned into the spotlight as applications of machine learning (ML). There, common challenges to the successful deployment of ML are domain-specific constraints, which lead to semantically constrained graphs. While much progress has been achieved in the generation of valid graphs for domain- and model-specific applications, a general approach has not been demonstrated yet. Here, we present a general-purpose, sequence-based, robust representation of semantically constrained graphs, which we call SELFIES (SELF-referencIng Embedded Strings). SELFIES are based on a Chomsky type-2 grammar, augmented with two self-referencing functions. We demonstrate their applicability to represent chemical compound structures and compare them to perhaps the most popular 2D representation, SMILES, and other important baselines. We find stronger robustness against character mutations while still maintaining similar chemical properties. Even entirely random SELFIES produce semantically valid graphs in most of the cases. As feature representation in variational autoencoders, SELFIES provide a substantial improvement in the task of in reconstruction, validity, and diversity. We anticipate that SELFIES allow for direct applications in ML, without the need for domain-specific adaptation of model architectures. SELFIES are not limited to the structures of small molecules, and we show how to apply them to two other examples from the sciences: representations of DNA and interaction graphs for quantum mechanical experiments.