Hungry Geese is a n-player variation of the popular game snake. This paper looks at state of the art Deep Reinforcement Learning Value Methods. The goal of the paper is to aggregate research of value based methods and apply it as an exercise to other environments. A vanilla Deep Q Network, a Double Q-network and a Dueling Q-Network were all examined and tested with the Hungry Geese environment. The best performing model was the vanilla Deep Q Network due to its simple state representation and smaller network structure. Converging towards an optimal policy was found to be difficult due to random geese initialization and food generation. Therefore we show that Deep Q Networks may not be the appropriate model for such a stochastic environment and lastly we present improvements that can be made along with more suitable models for the environment.

Self-supervised learning provides an opportunity to explore unlabeled chest X-rays and their associated free-text reports accumulated in clinical routine without manual supervision. This paper proposes a Joint Image Text Representation Learning Network (JoImTeRNet) for pre-training on chest X-ray images and their radiology reports. The model was pre-trained on both the global image-sentence level and the local image region-word level for visual-textual matching. Both are bidirectionally constrained on Cross-Entropy based and ranking-based Triplet Matching Losses. The region-word matching is calculated using the attention mechanism without direct supervision about their mapping. The pre-trained multi-modal representation learning paves the way for downstream tasks concerning image and/or text encoding. We demonstrate the representation learning quality by cross-modality retrievals and multilabel classifications on two datasets: OpenI-IU and MIMIC-CXR.

Spiking neural networks (SNNs) with leaky integrate and fire (LIF) neurons, can be operated in an event-driven manner and have internal states to retain information over time, providing opportunities for energy-efficient neuromorphic computing, especially on edge devices. Note, however, many representative works on SNNs do not fully demonstrate the usefulness of their inherent recurrence (membrane potentials retaining information about the past) for sequential learning. Most of the works train SNNs to recognize static images by artificially expanded input representation in time through rate coding. We show that SNNs can be trained for sequential tasks and propose modifications to a network of LIF neurons that enable internal states to learn long sequences and make their inherent recurrence resilient to the vanishing gradient problem. We then develop a training scheme to train the proposed SNNs with improved inherent recurrence dynamics. Our training scheme allows spiking neurons to produce multi-bit outputs (as opposed to binary spikes) which help mitigate the mismatch between a derivative of spiking neurons' activation function and a surrogate derivative used to overcome spiking neurons' non-differentiability. Our experimental results indicate that the proposed SNN architecture on TIMIT and LibriSpeech 100h dataset yields accuracy comparable to that of LSTMs (within 1.10% and 0.36%, respectively), but with 2x fewer parameters than LSTMs. The sparse SNN outputs also lead to 10.13x and 11.14x savings in multiplication operations compared to GRUs, which is generally con-sidered as a lightweight alternative to LSTMs, on TIMIT and LibriSpeech 100h datasets, respectively.

Camera anomalies like rain or dust can severelydegrade image quality and its related tasks, such as localizationand segmentation. In this work we address this importantissue by implementing a pre-processing step that can effectivelymitigate such artifacts in a real-time fashion, thus supportingthe deployment of autonomous systems with limited computecapabilities. We propose a shallow generator with aggregation,trained in an adversarial setting to solve the ill-posed problemof reconstructing the occluded regions. We add an enhancer tofurther preserve high-frequency details and image colorization.We also produce one of the largest publicly available datasets1to train our architecture and use realistic synthetic raindrops toobtain an improved initialization of the model. We benchmarkour framework on existing datasets and on our own imagesobtaining state-of-the-art results while enabling real-time per-formance, with up to 40x faster inference time than existingapproaches.

In recent years, neural paraphrase generation based on Seq2Seq has achieved superior performance, however, the generated paraphrase still has the problem of lack of diversity. In this paper, we focus on improving the diversity between the generated paraphrase and the original sentence, i.e., making generated paraphrase different from the original sentence as much as possible. We propose BTmPG (Back-Translation guided multi-round Paraphrase Generation), which leverages multi-round paraphrase generation to improve diversity and employs back-translation to preserve semantic information. We evaluate BTmPG on two benchmark datasets. Both automatic and human evaluation show BTmPG can improve the diversity of paraphrase while preserving the semantics of the original sentence.

Sleep stage classification is essential for sleep assessment and disease diagnosis. Although previous attempts to classify sleep stages have achieved high classification performance, several challenges remain open: 1) How to effectively utilize time-varying spatial and temporal features from multi-channel brain signals remains challenging. Prior works have not been able to fully utilize the spatial topological information among brain regions. 2) Due to the many differences found in individual biological signals, how to overcome the differences of subjects and improve the generalization of deep neural networks is important. 3) Most deep learning methods ignore the interpretability of the model to the brain. To address the above challenges, we propose a multi-view spatial-temporal graph convolutional networks (MSTGCN) with domain generalization for sleep stage classification. Specifically, we construct two brain view graphs for MSTGCN based on the functional connectivity and physical distance proximity of the brain regions. The MSTGCN consists of graph convolutions for extracting spatial features and temporal convolutions for capturing the transition rules among sleep stages. In addition, attention mechanism is employed for capturing the most relevant spatial-temporal information for sleep stage classification. Finally, domain generalization and MSTGCN are integrated into a unified framework to extract subject-invariant sleep features. Experiments on two public datasets demonstrate that the proposed model outperforms the state-of-the-art baselines.

Masked language modeling (MLM), a self-supervised pretraining objective, is widely used in natural language processing for learning text representations. MLM trains a model to predict a random sample of input tokens that have been replaced by a [MASK] placeholder in a multi-class setting over the entire vocabulary. When pretraining, it is common to use alongside MLM other auxiliary objectives on the token or sequence level to improve downstream performance (e.g. next sentence prediction). However, no previous work so far has attempted in examining whether other simpler linguistically intuitive or not objectives can be used standalone as main pretraining objectives. In this paper, we explore five simple pretraining objectives based on token-level classification tasks as replacements of MLM. Empirical results on GLUE and SQuAD show that our proposed methods achieve comparable or better performance to MLM using a BERT-BASE architecture. We further validate our methods using smaller models, showing that pretraining a model with 41% of the BERT-BASE's parameters, BERT-MEDIUM results in only a 1% drop in GLUE scores with our best objective.

How data is represented and operationalized is critical for building computational solutions that are both effective and efficient. A common approach is to represent data objects as binary vectors, denoted \textit{hash codes}, which require little storage and enable efficient similarity search through direct indexing into a hash table or through similarity computations in an appropriate space. Due to the limited expressibility of hash codes, compared to real-valued representations, a core open challenge is how to generate hash codes that well capture semantic content or latent properties using a small number of bits, while ensuring that the hash codes are distributed in a way that does not reduce their search efficiency. State of the art methods use representation learning for generating such hash codes, focusing on neural autoencoder architectures where semantics are encoded into the hash codes by learning to reconstruct the original inputs of the hash codes. This thesis addresses the above challenge and makes a number of contributions to representation learning that (i) improve effectiveness of hash codes through more expressive representations and a more effective similarity measure than the current state of the art, namely the Hamming distance, and (ii) improve efficiency of hash codes by learning representations that are especially suited to the choice of search method. The contributions are empirically validated on several tasks related to similarity search and recommendation.

Visual emotion analysis (VEA) has attracted great attention recently, due to the increasing tendency of expressing and understanding emotions through images on social networks. Different from traditional vision tasks, VEA is inherently more challenging since it involves a much higher level of complexity and ambiguity in human cognitive process. Most of the existing methods adopt deep learning techniques to extract general features from the whole image, disregarding the specific features evoked by various emotional stimuli. Inspired by the \textit{Stimuli-Organism-Response (S-O-R)} emotion model in psychological theory, we proposed a stimuli-aware VEA method consisting of three stages, namely stimuli selection (S), feature extraction (O) and emotion prediction (R). First, specific emotional stimuli (i.e., color, object, face) are selected from images by employing the off-the-shelf tools. To the best of our knowledge, it is the first time to introduce stimuli selection process into VEA in an end-to-end network. Then, we design three specific networks, i.e., Global-Net, Semantic-Net and Expression-Net, to extract distinct emotional features from different stimuli simultaneously. Finally, benefiting from the inherent structure of Mikel's wheel, we design a novel hierarchical cross-entropy loss to distinguish hard false examples from easy ones in an emotion-specific manner. Experiments demonstrate that the proposed method consistently outperforms the state-of-the-art approaches on four public visual emotion datasets. Ablation study and visualizations further prove the validity and interpretability of our method.

The wide application of smart devices enables the availability of multimodal data, which can be utilized in many tasks. In the field of multimodal sentiment analysis (MSA), most previous works focus on exploring intra- and inter-modal interactions. However, training a network with cross-modal information (language, visual, audio) is still challenging due to the modality gap, and existing methods still cannot ensure to sufficiently learn intra-/inter-modal dynamics. Besides, while learning dynamics within each sample draws great attention, the learning of inter-class relationships is neglected. Moreover, the size of datasets limits the generalization ability of existing methods. To address the afore-mentioned issues, we propose a novel framework HyCon for hybrid contrastive learning of tri-modal representation. Specifically, we simultaneously perform intra-/inter-modal contrastive learning and semi-contrastive learning (that is why we call it hybrid contrastive learning), with which the model can fully explore cross-modal interactions, preserve inter-class relationships and reduce the modality gap. Besides, a refinement term is devised to prevent the model falling into a sub-optimal solution. Moreover, HyCon can naturally generate a large amount of training pairs for better generalization and reduce the negative effect of limited datasets. Extensive experiments on public datasets demonstrate that our proposed method outperforms existing works.