In the area of credit risk analytics, current Bankruptcy Prediction Models (BPMs) struggle with (a) the availability of comprehensive and real-world data sets and (b) the presence of extreme class imbalance in the data (i.e., very few samples for the minority class) that degrades the performance of the prediction model. Moreover, little research has compared the relative performance of well-known BPM's on public datasets addressing the class imbalance problem. In this work, we apply eight classes of well-known BPMs, as suggested by a review of decades of literature, on a new public dataset named Freddie Mac Single-Family Loan-Level Dataset with resampling (i.e., adding synthetic minority samples) of the minority class to tackle class imbalance. Additionally, we apply some recent AI techniques (e.g., tree-based ensemble techniques) that demonstrate potentially better results on models trained with resampled data. In addition, from the analysis of 19 years (1999-2017) of data, we discover that models behave differently when presented with sudden changes in the economy (e.g., a global financial crisis) resulting in abrupt fluctuations in the national default rate. In summary, this study should aid practitioners/researchers in determining the appropriate model with respect to data that contains a class imbalance and various economic stages.

Department of Mathematics and Statistics McGill University Montreal, QC H3A 0E9 Canada Editor: Abstract We propose a novel approach to addressing the vanishing (or exploding) gradient problem in deep neural networks. We construct a new architecture for deep neural networks where all layers (except the output layer) of the network are a combination of rotation, permutation, diagonal, and activation sublayers which are all volume preserving. This control on the volume forces the gradient (on average) to maintain equilibrium and not explode or vanish. Volume-preserving neural networks train reliably, quickly and accurately and the learning rate is consistent across layers in deep volume-preserving neural networks. To demonstrate this we apply our volume-preserving neural network model to two standard datasets. Keywords: volume-preserving, neural network, machine learning, deep learning, vanishing gradient problem 1. Introduction Deep neural networks are characterized by the composition of a large number of functions (aka layers), each typically consisting of an affine transformation followed by a non-affine "activation function". Each layer is determined by a number of parameters which are trained on data to approximate some function. The deepness refers to the number of such functions composed (or the number of layers). The number of layers required to be deep is not well-defined, but an overview of deep learning (Schmidhuber, 2015) states that any 1 arXiv:1911.09576v2

Ling Pan 1, Qingpeng Cai 2, Longbo Huang 1 1 IIIS, Tsinghua University 2 Alibaba Group Abstract Recent years have witnessed a tremendous improvement of deep reinforcement learning. However, a challenging problem is that an agent may suffer from inefficient exploration, particularly for on-policy methods. Previous exploration methods either rely on complex structure to estimate the novelty of states, or incur sensitive hyper-parameters causing instability. In this paper, we propose an efficient exploration method, Multi-Path Policy Optimization (MPPO), which does not incur high computation cost and ensures stability. MPPO maintains an efficient mechanism that effectively utilizes a population of diverse policies to enable better exploration, especially in sparse environments. We also give a theoretical guarantee of the stable performance. We build our scheme upon two widely-adopted on-policy methods, the Trust-Region Policy Optimization (TRPO) algorithm and Proximal Policy Optimization (PPO) algorithm. We conduct extensive experiments on several MuJoCo tasks and their sparsified variants to fairly evaluate the proposed method. Results show that MPPO significantly outperforms state-of-the-art exploration methods in terms of both sample efficiency and final performance. 1 Introduction In reinforcement learning, an agent seeks to find an optimal policy that maximizes long-term rewards by interacting with an unknown environment. Directly optimizing the policy by vanilla policy gradient methods may incur large policy changes, which can result in performance collapse due to unlimited updates. To resolve this issue, Trust Region Policy Optimization (TRPO) (33) and Proximal Policy Optimization (PPO) (35) optimize a surrogate function in a conservative way, both being on-policy methods that perform policy updates based on samples collected by the current policy.

In deep reinforcement learning (RL), adversarial attacks can trick an agent into unwanted states and disrupt training. We propose a system called Robust Student-DQN (RS-DQN), which permits online robustness training alongside Q networks, while preserving competitive performance. We show that RS-DQN can be combined with (i) state-of-the-art adversarial training and (ii) provably robust training to obtain an agent that is resilient to strong attacks during training and evaluation.

In the design of artificially sentient robots, an obstacle always has been that conventional computers cannot really process information in parallel, whereas the human affective system is capable of producing experiences of emotional concurrency (e.g., happy and sad). Another schism that has been in the way is the persistent Cartesian divide between cognition and affect, whereas people easily can reflect on their emotions or have feelings about a thought. As an essentially theoretical exercise, we posit that quantum physics at the basis of neurology explains observations in cognitive emotion psychology from the belief that the construct of reality is partially imagined (Im) in the complex coordinate space C^3. We propose a quantum computational account to mixed states of reflection and affect, while transforming known psychological dimensions into the actual quantum dynamics of electromotive forces. As a precursor to actual simulations, we show examples of possible robot behaviors, using Einstein-Podolsky-Rosen circuits. Keywords: emotion, reflection, modelling, quantum computing

We present CoverNet, a new method for multimodal, probabilistic trajectory prediction in urban driving scenarios. Previous work has employed a variety of methods, including multimodal regression, occupancy maps, and 1-step stochastic policies. We instead frame the trajectory prediction problem as classification over a diverse set of trajectories. The size of this set remains manageable, due to the fact that there are a limited number of distinct actions that can be taken over a reasonable prediction horizon. We structure the trajectory set to a) ensure a desired level of coverage of the state space, and b) eliminate physically impossible trajectories. By dynamically generating trajectory sets based on the agent's current state, we can further improve the efficiency of our method. We demonstrate our approach on public, real-world self-driving datasets, and show that it outperforms state-of-the-art methods.

The paper provides an understanding of social capital in organizations that are open membership multi-agent systems with an emphasis in our formulation on the dynamic network of social interaction that, in part, elucidate evolving structures and impromptu topologies of networks. This paper, therefore, models an open source project as an organizational network. It provides definitions of social capital for this organizational network and formulation of the mechanism to optimize the social capital for achieving its goal that is optimized productivity. A case study of an open source Apache-Hadoop project is considered and empirically evaluated. An analysis of how social capital can be created within this type of organizations and driven to a measurement for its value is provided. Finally, a verification on whether the social capital of the organizational network is proportional towards optimizing their productivity is considered.

We propose a method for efficient training of deep Reinforcement Learning (RL) agents when the reward is highly sparse and non-Markovian, but at the same time admits a high-level yet unknown sequential structure, as seen in a number of video games. This high-level sequential structure can be expressed as a computer program, which our method infers automatically as the RL agent explores the environment. Through this process, a high-level sequential task that occurs only rarely may nonetheless be encoded within the inferred program. A hybrid architecture for deep neural fitted Q-iteration is then employed to fill in low-level details and generate an optimal control policy that follows the structure of the program. Our experiments show that the agent is able to synthesise a complex program to guide the RL exploitation phase, which is otherwise difficult to achieve with state-of-the-art RL techniques.

Although n-gram language models (LMs) have been outperformed by the state-of-the-art neural LMs, they are still widely used in speech recognition due to its high efficiency in inference. In this paper, we demonstrate that n-gram LM can be improved by neural LMs through a text generation based data augmentation method. In contrast to previous approaches, we employ a large-scale general domain pre-training followed by in-domain fine-tuning strategy to construct deep Transformer based neural LMs. Large amount of in-domain text data is generated with the well trained deep Transformer to construct new n-gram LMs, which are then interpolated with baseline n-gram systems. Empirical studies on different speech recognition tasks show that the proposed approach can effectively improve recognition accuracy. In particular, our proposed approach brings significant relative word error rate reduction up to 6.0% for domains with limited in-domain data.

For many NLP applications, such as question answering and summarisation, the goal is to select the best solution from a large space of candidates to meet a particular user's needs. To address the lack of user-specific training data, we propose an interactive text ranking approach that actively selects pairs of candidates, from which the user selects the best. Unlike previous strategies, which attempt to learn a ranking across the whole candidate space, our method employs Bayesian optimisation to focus the user's labelling effort on high quality candidates and integrates prior knowledge in a Bayesian manner to cope better with small data scenarios. We apply our method to community question answering (cQA) and extractive summarisation, finding that it significantly outperforms existing interactive approaches. We also show that the ranking function learned by our method is an effective reward function for reinforcement learning, which improves the state of the art for interactive summarisation.