China's vehicle insurers can expect huge disruption to their traditional business models, as the era of autonomous driving, powered by artificial intelligence (AI) continues to accelerate, a new study claims. Three-quarters of insurers expect vehicle premiums to be included in the price tags of cars while more than 60 per cent expect a drop in premiums collected from car owners, once self-driving models becomes commonplace on our roads, said a joint report published between the Insurance Society of China and Fudan University, released on Sunday. From damage assessment to the actual buying of insurance cover, AI is playing a far-reaching role in reshaping the country's car insurance sector, said market veterans commenting on the findings. "AI is casting a growing influence on insurance practitioners," said Yao Qinghai, chairman of the Insurance Society, speaking in Shanghai. "We urge the industry to get better prepared for a changing landscape, as many jobs could be replaced." The report was based on the views of 47 industry experts from insurers, regulators and fintech companies.

Inspired by how humans summarize long documents, we propose an accurate and fast summarization model that first selects salient sentences and then rewrites them abstractively (i.e., compresses and paraphrases) to generate a concise overall summary. We use a novel sentence-level policy gradient method to bridge the non-differentiable computation between these two neural networks in a hierarchical way, while maintaining language fluency. Empirically, we achieve the new state-of-the-art on all metrics (including human evaluation) on the CNN/Daily Mail dataset, as well as significantly higher abstractiveness scores. Moreover, by first operating at the sentence-level and then the word-level, we enable parallel decoding of our neural generative model that results in substantially faster (10-20x) inference speed as well as 4x faster training convergence than previous long-paragraph encoder-decoder models. We also demonstrate the generalization of our model on the test-only DUC-2002 dataset, where we achieve higher scores than a state-of-the-art model.

Knowledge of the importance of input features towards decisions made by machine-learning models is essential to increase our understanding of both the models and the underlying data. Here, we present a new approach to estimating feature importance with neural networks based on the idea of distributing the features of interest among experts in an attentive mixture of experts (AME). AMEs couple attentive gating networks with a Granger-causal objective to jointly produce accurate predictions as well as estimates of feature importance. Our experiments on an established benchmark and two real-world datasets show (i) that the feature importance estimates provided by AMEs compare favourably to those provided by state-of-the-art methods, (ii) that AMEs are significantly faster than existing methods, and (iii) that the associations discovered by AMEs are consistent with those reported by domain experts. In addition, we analyse the trade-off between predictive performance and estimation accuracy, the degree to which importance estimates of existing methods conform to predictive value, and whether a lower Granger-causal error on held-out data indicates a better feature importance estimation accuracy.

Teaching agents to perform tasks using Reinforcement Learning is no easy feat. As the goal of reinforcement learning agents is to maximize the accumulated reward, they often find loopholes and misspecifications in the reward signal which lead to unwanted behavior. To overcome this, often, regularization is employed through the technique of reward shaping - the agent is provided an additional weighted reward signal, meant to lead it towards a desired behavior. The weight is considered as a hyper-parameter and is selected through trial and error, a time consuming and computationally intensive task. In this work, we present a novel multi-timescale approach for constrained policy optimization, called, 'Reward Constrained Policy Optimization' (RCPO), which enables policy regularization without the use of reward shaping. We prove the convergence of our approach and provide empirical evidence of its ability to train constraint satisfying policies.

Humans excel at continually acquiring and fine-tuning knowledge over sustained time spans. This ability, typically referred to as lifelong learning, is crucial for artificial agents interacting in real-world, dynamic environments where i) the number of tasks to be learned is not pre-defined, ii) training samples become progressively available over time, and iii) annotated samples may be very sparse. In this paper, we propose a dual-memory self-organizing system that learns spatiotemporal representations from videos. The architecture draws inspiration from the interplay of the hippocampal and neocortical systems in the mammalian brain argued to mediate the complementary tasks of quickly integrating specific experiences, i.e., episodic memory (EM), and slowly learning generalities from episodic events, i.e., semantic memory (SM). The complementary memories are modeled as recurrent self-organizing neural networks: The EM quickly adapts to incoming novel sensory observations via competitive Hebbian Learning, whereas the SM progressively learns compact representations by using task-relevant signals to regulate intrinsic levels of neurogenesis and neuroplasticity. For the consolidation of knowledge, trajectories of neural reactivations are periodically replayed to both networks. We analyze and evaluate the performance of our approach with the CORe50 benchmark dataset for continuous object recognition from videos. We show that the proposed approach significantly outperforms current (supervised) methods of lifelong learning in three different incremental learning scenarios, and that due to the unsupervised nature of neural network self-organization, our approach can be used in scenarios where sample annotations are sparse.

Knowledge tracing (KT) refers to a machine learning technique to assess a student's level of understanding (so-called knowledge state) of a certain concept based on the student performance on problem solving. KT accepts a series of question-answer pairs as an input and iteratively updates the knowledge state of the student, eventually returning the probability of the student solving an unseen question. From the viewpoint of neuroeducation (the field of applying neuroscience, cognitive science, and psychology to education), however, KT leaves much room for improvement in terms of explaining the complex process of human learning. In this paper, we identify three problems of KT (namely non adaptive knowledge growth, neglected latent information, and unintended negative influence) and propose a memory-network-based technique named intelligent knowledge tracing (IKT) to address them, thus approaching one step closer to understanding the complex mechanism underlying human learning. In addition, we propose a new performance metric called correct update count (CUC) that can measure the degree of unintended negative influence, thus quantifying how closely a student model resembles the human learning process. The proposed CUC metric can complement the area under the curve (AUC) metric, allowing us to evaluate competing models more effectively. According to our experiments using a widely used public benchmark, IKT significantly (over two times) outperformed the existing KT approaches in terms of CUC, while preserving the correctness behavior measured in AUC.

On a constant quest for inspiration, designers can become more effective with tools that facilitate their creative process and let them overcome design fixation. This paper explores the practicality of applying neural style transfer as an emerging design tool for generating creative digital content. To this aim, the present work explores a well-documented neural style transfer algorithm (Johnson 2016) in four experiments on four relevant visual parameters: number of iterations, learning rate, total variation, content vs. style weight. The results allow a pragmatic recommendation of parameter configuration (number of iterations: 200 to 300, learning rate: 2e-1 to 4e-1, total variation: 1e-4 to 1e-8, content weights vs. style weights: 50:100 to 200:100) that saves extensive experimentation time and lowers the technical entry barrier. With this rule-of-thumb insight, visual designers can effectively apply deep learning to create artistic visual variations of digital content. This could enable designers to leverage AI for creating design works as state-of-the-art.

In this paper, we present a generative model to generate a natural language sentence describing a table region, e.g., a row. The model maps a row from a table to a continuous vector and then generates a natural language sentence by leveraging the semantics of a table. To deal with rare words appearing in a table, we develop a flexible copying mechanism that selectively replicates contents from the table in the output sequence. Extensive experiments demonstrate the accuracy of the model and the power of the copying mechanism. On two synthetic datasets, WIKIBIO and SIMPLEQUESTIONS, our model improves the current state-of-the-art BLEU-4 score from 34.70 to 40.26 and from 33.32 to 39.12, respectively. Furthermore, we introduce an open-domain dataset WIKITABLETEXT including 13,318 explanatory sentences for 4,962 tables. Our model achieves a BLEU-4 score of 38.23, which outperforms template based and language model based approaches.

An accurate abstractive summary of a document should contain all its salient information and should be logically entailed by the input document. We improve these important aspects of abstractive summarization via multi-task learning with the auxiliary tasks of question generation and entailment generation, where the former teaches the summarization model how to look for salient questioning-worthy details, and the latter teaches the model how to rewrite a summary which is a directed-logical subset of the input document. We also propose novel multi-task architectures with high-level (semantic) layer-specific sharing across multiple encoder and decoder layers of the three tasks, as well as soft-sharing mechanisms (and show performance ablations and analysis examples of each contribution). Overall, we achieve statistically significant improvements over the state-of- the-art on both the CNN/DailyMail and Gigaword datasets, as well as on the DUC-2002 transfer setup. We also present several quantitative and qualitative analysis studies of our model's learned saliency and entailment skills.

Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry and pose the challenges of not having adequate computing resources and of high costs involved in human labeling efforts. Training data subset selection and active learning techniques have been proposed as possible solutions to these challenges respectively. A special class of subset selection functions naturally model notions of diversity, coverage and representation and they can be used to eliminate redundancy and thus lend themselves well for training data subset selection. They can also help improve the efficiency of active learning in further reducing human labeling efforts by selecting a subset of the examples obtained using the conventional uncertainty sampling based techniques. In this work we empirically demonstrate the effectiveness of two diversity models, namely the Facility-Location and Disparity-Min models for training-data subset selection and reducing labeling effort. We do this for a variety of computer vision tasks including Gender Recognition, Scene Recognition and Object Recognition. Our results show that subset selection done in the right way can add 2-3% in accuracy on existing baselines, particularly in the case of less training data. This allows the training of complex machine learning models (like Convolutional Neural Networks) with much less training data while incurring minimal performance loss.