The need to efficiently calculate first- and higher-order derivatives of increasingly complex models expressed in Python has stressed or exceeded the capabilities of available tools. In this work, we explore techniques from the field of automatic differentiation (AD) that can give researchers expressive power, performance and strong usability. These include source-code transformation (SCT), flexible gradient surgery, efficient in-place array operations, higher-order derivatives as well as mixing of forward and reverse mode AD. We implement and demonstrate these ideas in the Tangent software library for Python, the first AD framework for a dynamic language that uses SCT.

Abstract--Time-continuous emotion prediction has become an increasingly compelling task in machine learning. Considerable efforts have been made to advance the performance of these systems. Nonetheless, the main focus has been the development of more sophisticated models and the incorporation of different expressive modalities (e. g., speech, face, and physiology). In this paper, motivated by the benefit of difficulty awareness in a human learning procedure, we propose a novel machine learning framework, namely, Dynamic Difficulty Awareness Training (DDAT), which sheds fresh light on the research - directly exploiting the difficulties in learning to boost the machine learning process. The DDAT framework consists of two stages: information retrieval and information exploitation. In the first stage, we make use of the reconstruction error of input features or the annotation uncertainty to estimate the difficulty of learning specific information. The obtained difficulty level is then used in tandem with original features to update the model input in a second learning stage with the expectation that the model can learn to focus on high difficulty regions of the learning process. We perform extensive experiments on a benchmark database (RECOLA) to evaluate the effectiveness of the proposed framework. The experimental results show that our approach outperforms related baselines as well as other well-established time-continuous emotion prediction systems, which suggests that dynamically integrating the difficulty information for neural networks can help enhance the learning process. Time-continuous emotion prediction systems have received widespread interest in the machine learning (ML) community over the past decade [1]-[3]. One of the main reasons for this interest is the fact that time-continuous emotion predictions can analyse subtle and complex affective states of humans over time and play a central role in smart conversational agents that aim to achieve a natural and intuitive interaction between humans and machines [2], [4]-[7]. Great efforts have been made in this field, and most of them can generally be classified into two strands. Z. Zhang is with GLAM - the Group on Language, Audio & Music, Imperial College London (UK).

ABSTRACT Vision-based navigation of modern autonomous vehicles primarily depends on Deep Neural Network (DNN) based systems in which the controller obtains input from sensors/detectors such as cameras, and produces an output such as a steering wheel angle to navigate the vehicle safely in roadway traffic. Typically, these DNN-based systems are trained through supervised and/or transfer learning; however, recent studies show that these systems can be compromised by perturbation or adversarial input features on the trained DNN-based models. Similarly, this perturbation can be introduced into the autonomous vehicle DNN-based system by roadway hazards such as debris and roadblocks. In this study, we first introduce a roadway hazardous environment (both intentional and unintentional) that can compromise the DNN-based system of an autonomous vehicle, producing an incorrect vehicle navigational output such as a steering wheel angle, which can cause crashes resulting in fatality and injury. Then, we develop an approach based on object detection and semantic segmentation to mitigate the adverse effect of this hazardous environment, one that helps the autonomous vehicle to navigate safely around such hazards. This study finds the DNN-based model with hazardous object detection, and semantic segmentation improves the ability of an autonomous vehicle to avoid potential crashes by 21% compared to the traditional DNN-based autonomous driving system.

This paper introduces a sentence to vector encoding framework suitable for advanced natural language processing. Our latent representation is shown to encode sentences with common semantic information with similar vector representations. The vector representation is extracted from an encoder-decoder model which is trained on sentence paraphrase pairs. We demonstrate the application of the sentence representations for two different tasks -- sentence paraphrasing and paragraph summarization, making it attractive for commonly used recurrent frameworks that process text. Experimental results help gain insight how vector representations are suitable for advanced language embedding.

Several recent projects demonstrated the promise of end-to-end learned deep visuomotor policies for robot manipulator control. Despite impressive progress, these systems are known to be vulnerable to physical disturbances, such as accidental or adversarial bumps that make them drop the manipulated object. They also tend to be distracted by visual disturbances such as objects moving in the robot's field of view, even if the disturbance does not physically prevent the execution of the task. In this paper we propose a technique for augmenting a deep visuomotor policy trained through demonstrations with task-focused attention. The manipulation task is specified with a natural language text such as "move the red bowl to the left". This allows the attention component to concentrate on the current object that the robot needs to manipulate. We show that even in benign environments, the task focused attention allows the policy to consistently outperform a variant with no attention mechanism. More importantly, the new policy is significantly more robust: it regularly recovers from severe physical disturbances (such as bumps causing it to drop the object) from which the unmodified policy almost never recovers. In addition, we show that the proposed policy performs correctly in the presence of a wide class of visual disturbances, exhibiting a behavior reminiscent of human selective attention experiments.

Graph convolutional network (GCN) provides a powerful means for graph-based semi-supervised tasks. However, as a localized first-order approximation of spectral graph convolution, the classic GCN can not take full advantage of unlabeled data, especially when the unlabeled node is far from labeled ones. To capitalize on the information from unlabeled nodes to boost the training for GCN, we propose a novel framework named Self-Ensembling GCN (SEGCN), which marries GCN with Mean Teacher - another powerful model in semi-supervised learning. SEGCN contains a student model and a teacher model. As a student, it not only learns to correctly classify the labeled nodes, but also tries to be consistent with the teacher on unlabeled nodes in more challenging situations, such as a high dropout rate and graph collapse. As a teacher, it averages the student model weights and generates more accurate predictions to lead the student. In such a mutual-promoting process, both labeled and unlabeled samples can be fully utilized for backpropagating effective gradients to train GCN. In three article classification tasks, i.e. Citeseer, Cora and Pubmed, we validate that the proposed method matches the state of the arts in the classification accuracy.

Deep neural networks trained for classification have been found to learn powerful image representations, which are also often used for other tasks such as comparing images w.r.t. their visual similarity. However, visual similarity does not imply semantic similarity. In order to learn semantically discriminative features, we propose to map images onto class centroids whose pair-wise dot products correspond to a measure of semantic similarity between classes. Such an embedding would not only improve image retrieval results, but could also facilitate integrating semantics for other tasks, e.g., novelty detection or few-shot learning. We introduce a deterministic algorithm for computing the class centroids directly based on prior world-knowledge encoded in a hierarchy of classes such as WordNet. Experiments on CIFAR-100 and ImageNet show that our learned semantic image embeddings improve the semantic consistency of image retrieval results by a large margin.

Another area where we see the application of ConvNets is in the prevention of fraud, which is a big concern for telecom companies. In a bid to develop algorithms that detect early potential frauds and/or prevent them, deep learning techniques, especially ConvNets are being used to detect fraudsters in mobile communications. In a research paper, published in Science Direct, fraud datasets culled from customer details records (CDR) are used and learning features are extracted and classified to fraudulent and non-fraudulent events activity. The paper revealed how deep convolution neural networks surpassed other traditional machine learning algorithms such as random forest, support vector machines and gradient boosting classifier, especially in terms of accuracy.

To begin with, we're here to emphasize once again that first of all, machine learning is a great tool to boost revenues and, if it happens, a nice side effect of using machine learning development is about to bring down the costs. What's more, this notion is essential to remember when speaking on principles that make machine learning tick in business realm for the main goal of any company is to sell and do it right being its information, products or services. But you are probably wondering what the steps to roaring trade are. Here, you need to ask yourself three important questions and decide what to sell, who your target audience is and how to attract their eyes and ears to your brand. Beyond that, you also need to pick the right timing to go all in selling.

The advanced feats we've seen machines do thus far have basically been examples of clever optimization techniques). So what does this learning process look like? First, weight and bias values are propagated forward through the model to arrive at a predicted output. At each neuron/node, the linear combination of the inputs is then multiplied by an activation function as described above-- the sigmoid function in our example. This process by which weights and biases are propagated from inputs to output is called forward propagation. After arriving at the predicted output, the loss for the training example is calculated.