Unsupervised learning requiring only raw data is not only a fundamental function of the cerebral cortex, but also a foundation for a next generation of artificial neural networks. However, a unified theoretical framework to treat sensory inputs, synapses and neural activity together is still lacking. The computational obstacle originates from the discrete nature of synapses, and complex interactions among these three essential elements of learning. Here, we propose a variational mean-field theory in which only the distribution of synaptic weight is considered. The unsupervised learning can then be decomposed into two interwoven steps: a maximization step is carried out as a gradient ascent of the lower-bound on the data log-likelihood, and an expectation step is carried out as a message passing procedure on an equivalent or dual neural network whose parameter is specified by the variational parameter of the weight distribution. Therefore, our framework explains how data (or sensory inputs), synapses and neural activities interact with each other to achieve the goal of extracting statistical regularities in sensory inputs. This variational framework is verified in restricted Boltzmann machines with planted synaptic weights and learning handwritten digits.

Computer-assisted synthesis planning aims to help chemists find better reaction pathways faster. Finding viable and short pathways from sugar molecules to value-added chemicals can be modeled as a retrosynthesis planning problem with a catalyst allowed. This is a crucial step in efficient biomass conversion. The traditional computational chemistry approach to identifying possible reaction pathways involves computing the reaction energies of hundreds of intermediates, which is a critical bottleneck in silico reaction discovery. Deep reinforcement learning has shown in other domains that a well-trained agent with little or no prior human knowledge can surpass human performance. While some effort has been made to adapt machine learning techniques to the retrosynthesis planning problem, value-added chemical discovery presents unique challenges. Specifically, the reaction can occur in several different sites in a molecule, a subtle case that has never been treated in previous works. With a more versatile formulation of the problem as a Markov decision process, we address the problem using deep reinforcement learning techniques and present promising preliminary results.

Recently very deep transformers start showing outperformed performance to traditional bi-directional long short-term memory networks by a large margin. However, to put it into production usage, inference computation cost and latency are still serious concerns in real scenarios. In this paper, we study a novel non-autoregressive transformers structure for speech recognition, which is originally introduced in machine translation. During training input tokens fed to the decoder are randomly replaced by a special mask token. The network is required to predict those mask tokens by taking both context and input speech into consideration. During inference, we start from all mask tokens and the network gradually predicts all tokens based on partial results. We show this framework can support different decoding strategies, including traditional left-to-right. A new decoding strategy is proposed as an example, which starts from the easiest predictions to difficult ones. Some preliminary results on Aishell and CSJ benchmarks show the possibility to train such a non-autoregressive network for ASR. Especially in Aishell, the proposed method outperformed Kaldi nnet3 and chain model setup and is quite closed to the performance of the start-of-the-art end-to-end model.

Learning optimal resource allocation policies in wireless systems can be effectively achieved by formulating finite dimensional constrained programs which depend on system configuration, as well as the adopted learning parameterization. The interest here is in cases where system models are unavailable, prompting methods that probe the wireless system with candidate policies, and then use observed performance to determine better policies. This generic procedure is difficult because of the need to cull accurate gradient estimates out of these limited system queries. This paper constructs and exploits smoothed surrogates of constrained ergodic resource allocation problems, the gradients of the former being representable exactly as averages of finite differences that can be obtained through limited system probing. Leveraging this unique property, we develop a new model-free primal-dual algorithm for learning optimal ergodic resource allocations, while we rigorously analyze the relationships between original policy search problems and their surrogates, in both primal and dual domains. First, we show that both primal and dual domain surrogates are uniformly consistent approximations of their corresponding original finite dimensional counterparts. Upon further assuming the use of near-universal policy parameterizations, we also develop explicit bounds on the gap between optimal values of initial, infinite dimensional resource allocation problems, and dual values of their parameterized smoothed surrogates. In fact, we show that this duality gap decreases at a linear rate relative to smoothing and universality parameters. Thus, it can be made arbitrarily small at will, also justifying our proposed primal-dual algorithmic recipe. Numerical simulations confirm the effectiveness of our approach.

Variational Autoencoders (VAEs) hold great potential for modelling text, as they could in theory separate high-level semantic and syntactic properties from local regularities of natural language. Practically, however, VAEs with autoregressive decoders often suffer from posterior collapse, a phenomenon where the model learns to ignore the latent variables, causing the sequence VAE to degenerate into a language model. Previous works attempt to solve this problem with complex architectural changes or costly optimization schemes. In this paper, we argue that posterior collapse is caused in part by the encoder network failing to capture the input variabilities. We verify this hypothesis empirically and propose a straightforward fix using pooling. This simple technique effectively prevents posterior collapse, allowing the model to achieve significantly better data log-likelihood than standard sequence VAEs. Compared to the previous SOTA on preventing posterior collapse, we are able to achieve comparable performances while being significantly faster.

The progress of deep convolutional neural networks has been successfully exploited in various real-time computer vision tasks such as image classification and segmentation. Owing to the development of computational units, availability of digital datasets, and improved performance of deep learning models, fully automatic and accurate tracking of tongue contours in real-time ultrasound data became practical only in recent years. Recent studies have shown that the performance of deep learning techniques is significant in the tracking of ultrasound tongue contours in real-time applications such as pronunciation training using multimodal ultrasound-enhanced approaches. Due to the high correlation between ultrasound tongue datasets, it is feasible to have a general model that accomplishes automatic tongue tracking for almost all datasets. In this paper, we proposed a deep learning model comprises of a convolutional module mimicking the peripheral vision ability of the human eye to handle real-time, accurate, and fully automatic tongue contour tracking tasks, applicable for almost all primary ultrasound tongue datasets. Qualitative and quantitative assessment of IrisNet on different ultrasound tongue datasets and PASCAL VOC2012 revealed its outstanding generalization achievement in compare with similar techniques.

Current neural Natural Language Generation (NLG) models cannot handle emerging conditions due to their joint end-to-end learning fashion. When the need for generating text under a new condition emerges, these techniques require not only sufficiently supplementary labeled data but also a full re-training of the existing model. In this paper, we present a new framework named Hierarchical Neural Auto-Encoder (HAE) toward flexible conditional text generation. HAE decouples the text generation module from the condition representation module to allow "one-to-many" conditional generation. When a fresh condition emerges, only a lightweight network needs to be trained and works as a plug-in for HAE, which is efficient and desirable for real-world applications. Extensive experiments demonstrate the superiority of HAE against the existing alternatives with much less training time and fewer model parameters.

Neural networks are surprisingly good at interpolating and perform remarkably well when the training set examples resemble those in the test set. However, they are often unable to extrapolate patterns beyond the seen data, even when the abstractions required for such patterns are simple. In this paper, we first review the notion of extrapolation, why it is important and how one could hope to tackle it. We then focus on a specific type of extrapolation which is especially useful for natural language processing: generalization to sequences that are longer than the training ones. We hypothesize that models with a separate content- and location-based attention are more likely to extrapolate than those with common attention mechanisms. We empirically support our claim for recurrent seq2seq models with our proposed attention on variants of the Lookup Table task. This sheds light on some striking failures of neural models for sequences and on possible methods to approaching such issues.

When translating natural language questions into SQL queries to answer questions from a database, contemporary semantic parsing models struggle to generalize to unseen database schemas. The generalization challenge lies in (a) encoding the database relations in an accessible way for the semantic parser, and (b) modeling alignment between database columns and their mentions in a given query. We present a unified framework, based on the relation-aware self-attention mechanism, to address schema encoding, schema linking, and feature representation within a text-to-SQL encoder. On the challenging Spider dataset this framework boosts the exact match accuracy to 53.7%, compared to 47.4% for the state-of-the-art model unaugmented with BERT em-beddings. In addition, we observe qualitative improvements in the model's understanding of schema linking and alignment.

Deep learning has revolutionized speech recognition, image recognition, and natural language processing since 2010, each involving a single modality in the input signal. However, many applications in artificial intelligence involve more than one modality. It is therefore of broad interest to study the more difficult and complex problem of modeling and learning across multiple modalities. In this paper, a technical review of the models and learning methods for multimodal intelligence is provided. The main focus is the combination of vision and natural language, which has become an important area in both computer vision and natural language processing research communities. This review provides a comprehensive analysis of recent work on multimodal deep learning from three new angles - learning multimodal representations, the fusion of multimodal signals at various levels, and multimodal applications. On multimodal representation learning, we review the key concept of embedding, which unifies the multimodal signals into the same vector space and thus enables cross-modality signal processing. We also review the properties of the many types of embedding constructed and learned for general downstream tasks. On multimodal fusion, this review focuses on special architectures for the integration of the representation of unimodal signals for a particular task. On applications, selected areas of a broad interest in current literature are covered, including caption generation, text-to-image generation, and visual question answering. We believe this review can facilitate future studies in the emerging field of multimodal intelligence for the community.