Electronically excited states of molecules are at the heart of photochemistry, photophysics, as well as photobiology and also play a role in material science. Their theoretical description requires highly accurate quantum chemical calculations, which are computationally expensive. In this review, we focus on how machine learning is employed not only to speed up such excited-state simulations but also how this branch of artificial intelligence can be used to advance this exciting research field in all its aspects. Discussed applications of machine learning for excited states include excited-state dynamics simulations, static calculations of absorption spectra, as well as many others. In order to put these studies into context, we discuss the promises and pitfalls of the involved machine learning techniques. Since the latter are mostly based on quantum chemistry calculations, we also provide a short introduction into excited-state electronic structure methods, approaches for nonadiabatic dynamics simulations and describe tricks and problems when using them in machine learning for excited states of molecules.

The Variational Autoencoder (VAE) is a powerful framework for learning probabilistic latent variable generative models. However, typical assumptions on the approximate posterior distribution of the encoder and/or the prior, seriously restrict its capacity for inference and generative modeling. Variational inference based on neural autoregressive models respects the conditional dependencies of the exact posterior, but this flexibility comes at a cost: such models are expensive to train in high-dimensional regimes and can be slow to produce samples. In this work, we introduce an orthogonal solution, which we call self-reflective inference. By redesigning the hierarchical structure of existing VAE architectures, self-reflection ensures that the stochastic flow preserves the factorization of the exact posterior, sequentially updating the latent codes in a recurrent manner consistent with the generative model. We empirically demonstrate the clear advantages of matching the variational posterior to the exact posterior - on binarized MNIST, self-reflective inference achieves state-of-the art performance without resorting to complex, computationally expensive components such as autoregressive layers. Moreover, we design a variational normalizing flow that employs the proposed architecture, yielding predictive benefits compared to its purely generative counterpart. Our proposed modification is quite general and complements the existing literature; self-reflective inference can naturally leverage advances in distribution estimation and generative modeling to improve the capacity of each layer in the hierarchy.

Healthcare providers are increasingly using learned methods to predict and understand long-term patient outcomes in order to make meaningful interventions. However, despite innovations in this area, deep learning models often struggle to match performance of shallow linear models in predicting these outcomes, making it difficult to leverage such techniques in practice. In this work, motivated by the task of clinical prediction from insurance claims, we present a new technique called reverse distillation which pretrains deep models by using high-performing linear models for initialization. We make use of the longitudinal structure of insurance claims datasets to develop Self Attention with Reverse Distillation, or SARD, an architecture that utilizes a combination of contextual embedding, temporal embedding and self-attention mechanisms and most critically is trained via reverse distillation. SARD outperforms state-of-the-art methods on multiple clinical prediction outcomes, with ablation studies revealing that reverse distillation is a primary driver of these improvements.

Computing goal-directed behavior (sequential decision-making, or planning) is essential to designing efficient AI systems. Due to the computational complexity of planning, current approaches rely primarily upon hand-coded symbolic domain models and hand-coded heuristic-function generators for efficiency. Learned heuristics for such problems have been of limited utility as they are difficult to apply to problems with objects and object quantities that are significantly different from those in the training data. This paper develops a new approach for learning generalized heuristics in the absence of symbolic domain models using deep neural networks that utilize an input predicate vocabulary but are agnostic to object names and quantities. It uses an abstract state representation to facilitate data efficient, generalizable learning. Empirical evaluation on a range of benchmark domains show that in contrast to prior approaches, generalized heuristics computed by this method can be transferred easily to problems with different objects and with object quantities much larger than those in the training data.

We propose a Short-term Traffic flow Prediction (STP) framework so that transportation authorities take early actions to control flow and prevent congestion. We anticipate flow at future time frames on a target road segment based on historical flow data and innovative features such as real time feeds and trajectory data provided by Connected Vehicles (CV) technology. To cope with the fact that existing approaches do not adapt to variation in traffic, we show how this novel approach allows advanced modelling by integrating into the forecasting of flow, the impact of the various events that CV realistically encountered on segments along their trajectory. We solve the STP problem with a Deep Neural Networks (DNN) in a multitask learning setting augmented by input from CV. Results show that our approach, namely MTL-CV, with an average Root-Mean-Square Error (RMSE) of 0.052, outperforms state-of-the-art ARIMA time series (RMSE of 0.255) and baseline classifiers (RMSE of 0.122). Compared to single task learning with Artificial Neural Network (ANN), ANN had a lower performance, 0.113 for RMSE, than MTL-CV. MTL-CV learned historical similarities between segments, in contrast to using direct historical trends in the measure, because trends may not exist in the measure but do in the similarities.

This paper investigates how end-to-end driving models can be improved to drive more accurately and human-like. To tackle the first issue we exploit semantic and visual maps from HERE Technologies and augment the existing Drive360 dataset with such. The maps are used in an attention mechanism that promotes segmentation confidence masks, thus focusing the network on semantic classes in the image that are important for the current driving situation. Human-like driving is achieved using adversarial learning, by not only minimizing the imitation loss with respect to the human driver but by further defining a discriminator, that forces the driving model to produce action sequences that are human-like. Our models are trained and evaluated on the Drive360 + HERE dataset, which features 60 hours and 3000 km of real-world driving data. Extensive experiments show that our driving models are more accurate and behave more human-like than previous methods.

The increasing rise in machine learning and deep learning applications is requiring ever more computational resources to successfully meet the growing demands of an always-connected, automated world. Neuromorphic technologies based on Spiking Neural Network algorithms hold the promise to implement advanced artificial intelligence using a fraction of the computations and power requirements by modeling the functioning, and spiking, of the human brain. With the proliferation of tools and platforms aiding data scientists and machine learning engineers to develop the latest innovations in artificial and deep neural networks, a transition to a new paradigm will require building from the current well-established foundations. This paper explains the theoretical workings of neuromorphic technologies based on spikes, and overviews the state-of-art in hardware processors, software platforms and neuromorphic sensing devices. A progression path is paved for current machine learning specialists to update their skillset, as well as classification or predictive models from the current generation of deep neural networks to SNNs. This can be achieved by leveraging existing, specialized hardware in the form of SpiNNaker and the Nengo migration toolkit. First-hand, experimental results of converting a VGG-16 neural network to an SNN are shared. A forward gaze into industrial, medical and commercial applications that can readily benefit from SNNs wraps up this investigation into the neuromorphic computing future.

Generating an investment strategy using advanced deep learning methods in stock markets has recently been a topic of interest. Most existing deep learning methods focus on proposing an optimal model or network architecture by maximizing return. However, these models often fail to consider and adapt to the continuously changing market conditions. In this paper, we propose the Multi-Agent reinforcement learning-based Portfolio management System (MAPS). MAPS is a cooperative system in which each agent is an independent "investor" creating its own portfolio. In the training procedure, each agent is guided to act as diversely as possible while maximizing its own return with a carefully designed loss function. As a result, MAPS as a system ends up with a diversified portfolio. Experiment results with 12 years of US market data show that MAPS outperforms most of the baselines in terms of Sharpe ratio. Furthermore, our results show that adding more agents to our system would allow us to get a higher Sharpe ratio by lowering risk with a more diversified portfolio.

Have you ever heard about the Jennifer Aniston neuron? In 2005, a group of neuroscientists led by Rodrigo Quian Quiroga published a paper detailing his discovery of a type of neuron that steadily fired whenever the person was shown a photo of Jennifer Aniston. The neuron in question was not activated when presented with photos of other celebrities. Obviously, we don’t all have Jennifer Aniston neurons and those specialized neurons can be activated in response to pictures of other celebrities. However, the Aniston neuron has become one of the most powerful metaphors in neuroscience to describe neurons that focus on a very specific task.

Modern computational organic chemistry is becoming increasingly data-driven. There remain a large number of important unsolved problems in this area such as product prediction given reactants, drug discovery, and metric-optimized molecule synthesis, but efforts to solve these problems using machine learning have also increased in recent years. In this work, we propose the use of attention to study functional groups and other property-impacting molecular substructures from a data-driven perspective, using an transformer-based model (BERT) on datasets of string representations of molecules and analyzing the behavior of its attention heads. We then apply the representations of functional groups and atoms learned by the model to tackle problems of toxicity, solubility, drug-likeness, and synthesis accessibility on smaller datasets using the learned representations as features for graph convolution and attention models on the graph structure of molecules, as well as fine-tuning of BERT. Finally, we propose the use of attention visualization as a helpful tool for chemistry practitioners and students to quickly identify important substructures in various chemical properties.