Sentiment analysis benefits from large, hand-annotated resources in order to train and test machine learning models, which are often data hungry. While some languages, e.g., English, have a vast arrayof these resources, most under-resourced languages do not, especially for fine-grained sentiment tasks, such as aspect-level or targeted sentiment analysis. To improve this situation, we propose a cross-lingual approach to sentiment analysis that is applicable to under-resourced languages and takes into account target-level information. This model incorporates sentiment information into bilingual distributional representations, byjointly optimizing them for semantics and sentiment, showing state-of-the-art performance at sentence-level when combined with machine translation. The adaptation to targeted sentiment analysis on multiple domains shows that our model outperforms other projection-based bilingual embedding methods on binary targetedsentiment tasks. Our analysis on ten languages demonstrates that the amount of unlabeled monolingual data has surprisingly little effect on the sentiment results. As expected, the choice of a annotated source language for projection to a target leads to better results for source-target language pairs which are similar. Therefore, our results suggest that more efforts should be spent on the creation of resources for less similar languages tothose which are resource-rich already. Finally, a domain mismatch leads to a decreased performance. This suggests resources in any language should ideally cover varieties of domains.

Consistency is one of the major challenges faced by dialogue agents. A human-like dialogue agent should not only respond naturally, but also maintain a consistent persona. In this paper, we exploit the advantages of natural language inference (NLI) technique to address the issue of generating persona consistent dialogues. Different from existing work that re-ranks the retrieved responses through an NLI model, we cast the task as a reinforcement learning problem and propose to exploit the NLI signals from response-persona pairs as rewards for the process of dialogue generation. Specifically, our generator employs an attention-based encoder-decoder to generate persona-based responses. Our evaluator consists of two components: an adversarially trained naturalness module and an NLI based consistency module. Moreover, we use another well-performed NLI model in the evaluation of persona-consistency. Experimental results on both human and automatic metrics, including the model-based consistency evaluation, demonstrate that the proposed approach outperforms strong generative baselines, especially in the persona-consistency of generated responses.

Traffic sign identification using camera images from vehicles plays a critical role in autonomous driving and path planning. However, the front camera images can be distorted due to blurriness, lighting variations and vandalism which can lead to degradation of detection performances. As a solution, machine learning models must be trained with data from multiple domains, and collecting and labeling more data in each new domain is time consuming and expensive. In this work, we present an end-to-end framework to augment traffic sign training data using optimal reinforcement learning policies and a variety of Generative Adversarial Network (GAN) models, that can then be used to train traffic sign detector modules. Our automated augmenter enables learning from transformed nightime, poor lighting, and varying degrees of occlusions using the LISA Traffic Sign and BDD-Nexar dataset. The proposed method enables mapping training data from one domain to another, thereby improving traffic sign detection precision/recall from 0.70/0.66 to 0.83/0.71 for nighttime images.

--Energy disaggregation, also referred to as a Non-Intrusive Load Monitoring (NILM), is the task of using an aggregate energy signal, for example coming from a whole-home power monitor, to make inferences about the different individual loads of the system. In this paper, we present a novel approach based on the encoder-decoder deep learning framework with an attention mechanism for solving NILM. The attention mechanism is inspired by the temporal attention mechanism that has been recently applied to get state-of-the-art results in neural machine translation, text summarization and speech recognition. The experiments have been conducted on two publicly available datasets AMPds and UK-DALE in seen and unseen conditions. The results show that our proposed deep neural network outperforms the state-of-the-art Denoising Auto-Encoder (DAE) proposed initially by Kelly and Knottenbely (2015) and its extended and improved architecture by Bonfigli et al. (2018), in all the addressed experimental conditions. We also show that modeling attention translates into the ability to correctly detect the state change of each appliance, that is of extreme interest in the field of energy disaggregation. Non-Intrusive Load Monitoring (NILM) is the task of estimating the power demand of each appliance given aggregate power demand signal recorded by a single electric meter monitoring multiple appliances [1]. In the last years, the research on NILM has been particularly active in the field of machine learning.

In the past few years, deep learning has transformed artificial intelligence research and led to impressive performance in various difficult tasks. However, it is still unclear how the brain can perform credit assignment across many areas as efficiently as backpropagation does in deep neural networks. In this paper, we introduce a model that relies on a new role for a neuronal inhibitory machinery, referred to as ghost units. By cancelling the feedback coming from the upper layer when no target signal is provided to the top layer, the ghost units enables the network to backpropagate errors and do efficient credit assignment in deep structures. While considering one-compartment neurons and requiring very few biological assumptions, it is able to approximate the error gradient and achieve good performance on classification tasks. Error backpropagation occurs through the recurrent dynamics of the network and thanks to biologically plausible local learning rules. In particular, it does not require separate feedforward and feedback circuits. Different mechanisms for cancelling the feedback were studied, ranging from complete duplication of the connectivity by long term processes to online replication of the feedback activity. This reduced system combines the essential elements to have a working biologically abstracted analogue of backpropagation with a simple formulation and proofs of the associated results. Therefore, this model is a step towards understanding how learning and memory are implemented in cortical multilayer structures, but it also raises interesting perspectives for neuromorphic hardware.

Determining the primary site of origin for metastatic tumors is one of the open problems in cancer care because the efficacy of treatment often depends on the cancer tissue of origin. Classification methods that can leverage tumor genomic data and predict the site of origin are therefore of great value. Because tumor DNA point mutation data is very sparse, only limited accuracy (64.5% for 12 tumor classes) was previously demonstrated by methods that rely on point mutations as features (1). Tumor classification accuracy can be greatly improved (to over 90% for 33 classes) by relying on gene expression data (2). However, this additional data is often not readily available in clinical setting, because point mutations are better profiled and targeted by clinical mutational profiling. Here we sought to develop an accurate deep transfer learning and fine-tuning method for tumor sub-type classification, where predicted class is indicative of the primary site of origin. Our method significantly outperforms the state-of-the-art for tumor classification using DNA point mutations, reducing the error by more than 30% at the same time discriminating over many more classes on The Cancer Genome Atlas (TCGA) dataset. Using our method, we achieve state-of-the-art tumor type classification accuracy of 78.3% for 29 tumor classes relying on DNA point mutations in the tumor only.

These iterative optimization algorithms are computational expensive and difficult to converge. Unlike iterative optimization methods, supervised machine learning using two stage training-testing becomes a great advantage for fast real-time inference since the most expensive computations are performed during training. Deep Learning plays a very important role tackling these type of problems but requires large dataset to train the multi-layer model parameters of the network [1]. Here, we are interested in creating a molecular image dataset including shape images from real space and diffraction patterns from reciprocal space for machine learning practices. We call this dataset Molecular-MNIST because it consists 10 different size of molecules where each molecule has 2,000 structural variants - in an analogy of the famous 10-digit handwritten dataset MNIST [2]. 2. Molecular-MNIST Dataset 2.1.

In recent years, Convolutional Neural Network (CNN) based methods have achieved great success in a large number of applications and have been among the most powerful and widely used techniques in computer vision. However, CNN-based methods are computational-intensive and resource-consuming, and thus are hard to be integrated into embedded systems such as smart phones, smart glasses, and robots. FPGA is one of the most promising platforms for accelerating CNN, but the limited on-chip memory size limit the performance of FPGA accelerator for CNN. In this paper, we propose a framework for designing CNN accelerator on embedded FPGA for image classification. The proposed framework provides a tool for FPGA resource-aware design space exploration of CNNs and automatically generates the hardware description of the CNN to be programmed on a target FPGA. The framework consists of three main backends; software, hardware generation, and simulation/precision adjustment. The software backend serves as an API to the designer to design the CNN and train it according to the hardware resources that are available. Using the CNN model, hardware backend generates the necessary hardware components and integrates them to generate the hardware description of the CNN. Finaly, Simulation/precision adjustment backend adjusts the inter-layer precision units to minimize the classification error. We used 16-bit fixed-point data in a CNN accelerator (FPGA) and compared it to the exactly similar software version running on an ARM processor (32-bit floating point data). We encounter about 3% accuracy loss in classification of the accelerated (FPGA) version. In return, we got up to 15.75x speedup by classifying with the accelerated version on the FPGA.

To improve real-world applications of machine learning, experienced modelers develop intuition about their datasets, their models, and how the two interact. Manual inspection of raw data - of representative samples, of outliers, of misclassifications - is an essential tool in a) identifying and fixing problems in the data, b) generating new modeling hypotheses, and c) assigning or refining human-provided labels. However, manual data inspection is problematic for privacy sensitive datasets, such as those representing the behavior of real-world individuals. Furthermore, manual data inspection is impossible in the increasingly important setting of federated learning, where raw examples are stored at the edge and the modeler may only access aggregated outputs such as metrics or model parameters. This paper demonstrates that generative models - trained using federated methods and with formal differential privacy guarantees - can be used effectively to debug many commonly occurring data issues even when the data cannot be directly inspected. We explore these methods in applications to text with differentially private federated RNNs and to images using a novel algorithm for differentially private federated GANs.

In multi-label learning, each instance is associated with multiple labels and the crucial task is how to leverage label correlations in building models. Deep neural network methods usually jointly embed the feature and label information into a latent space to exploit label correlations. However, the success of these methods highly depends on the precise choice of model depth. Deep forest is a recent deep learning framework based on tree model ensembles, which does not rely on backpropagation. We consider the advantages of deep forest models are very appropriate for solving multi-label problems. Therefore we design the Multi-Label Deep Forest (MLDF) method with two mechanisms: measure-aware feature reuse and measure-aware layer growth. The measure-aware feature reuse mechanism reuses the good representation in the previous layer guided by confidence. The measure-aware layer growth mechanism ensures MLDF gradually increase the model complexity by performance measure. MLDF handles two challenging problems at the same time: one is restricting the model complexity to ease the overfitting issue; another is optimizing the performance measure on user's demand since there are many different measures in the multi-label evaluation. Experiments show that our proposal not only beats the compared methods over six measures on benchmark datasets but also enjoys label correlation discovery and other desired properties in multi-label learning.