Using the top solution from our type system optimization, we can now label data from Wikipedia using labels generated by the type system. Using this data (in our experiments, 400M tokens for each of English and French), we can now train a bidirectional LSTM to independently predict all the type memberships for each word. On the Wikipedia source text, we only have supervision on intra-wiki links, however this is sufficient to train a deep neural network to predict type membership with an F1 of over 0.91. One of our type systems, discovered by beam search, includes types such as Aviation, Clothing, and Games (as well as surprisingly specific ones like 1754 in Canada -- indicating 1754 was an exciting year in the dataset of 1,000 Wikipedia articles it was trained on); you can also view the full type system. Predicting entities in a document usually relies on a "coherence" metric between different entities, e.g.

This is Part 1 of the PyTorch Primer Series. It's a Python based package for serving as a replacement of Numpy and to provide flexibility as a Deep Learning Development Platform. I encourage you to read Fast AI's blog post for the reason of the course's switch to PyTorch. Tensors are similar to numpy's ndarrays, with the addition being that Tensors can also be used on a GPU to accelerate computing. Tensors are multi dimensional Matrices.

Temporal gates play a significant role in modern recurrent-based neural encoders, enabling fine-grained control over recursive compositional operations over time. In recurrent models such as the long short-term memory (LSTM), temporal gates control the amount of information retained or discarded over time, not only playing an important role in influencing the learned representations but also serving as a protection against vanishing gradients. This paper explores the idea of learning temporal gates for sequence pairs (question and answer), jointly influencing the learned representations in a pairwise manner. In our approach, temporal gates are learned via 1D convolutional layers and then subsequently cross applied across question and answer for joint learning. Empirically, we show that this conceptually simple sharing of temporal gates can lead to competitive performance across multiple benchmarks. Intuitively, what our network achieves can be interpreted as learning representations of question and answer pairs that are aware of what each other is remembering or forgetting, i.e., pairwise temporal gating. Via extensive experiments, we show that our proposed model achieves state-of-the-art performance on two community-based QA datasets and competitive performance on one factoid-based QA dataset.

Many efforts have been taken to train spiking neural networks (SNNs), but most of them still need improvements due to the discontinuous and non-differential characteristics of SNNs. While the mammalian brains solve these kinds of problems by integrating a series of biological plasticity learning rules. In this paper, we will focus on two biological plausible methodologies and try to solve these catastrophic training problems in SNNs. Firstly, the biological neural network will try to keep a balance between inputs and outputs on both the neuron and the network levels. Secondly, the biological synaptic weights will be passively updated by the changes of the membrane potentials of the neighbour-hood neurons, and the plasticity of synapses will not propagate back to other previous layers. With these biological inspirations, we propose Voltage-driven Plasticity-centric SNN (VPSNN), which includes four steps, namely: feed forward inference, unsupervised equilibrium state learning, supervised last layer learning and passively updating synaptic weights based on spike-timing dependent plasticity (STDP). Finally we get the accuracy of 98.52% on the hand-written digits classification task on MNIST. In addition, with the help of a visualization tool, we try to analyze the black box of SNN and get better understanding of what benefits have been acquired by the proposed method.

Matching pedestrians across multiple camera views has attracted lots of recent research attention due to its apparent importance in surveillance and security applications.While most existing works address this problem in a still-image setting, we consider the more informative and challenging video-based person re-identification problem, where a video of a pedestrian as seen in one camera needs to be matched to a gallery of videos captured by other non-overlapping cameras. We employ a convolutional network to extract the appearance and motion features from raw video sequences, and then feed them into a multi-rate recurrent network to exploit the temporal correlations, and more importantly, to take into account the fact that pedestrians, sometimes even the same pedestrian, move in different speeds across different camera views. The combined network is trained in an end-to-end fashion, and we further propose an initialization strategy via context reconstruction to largely improve the performance. We conduct extensive experiments on the iLIDS-VID and PRID-2011 datasets, and our experimental results confirm the effectiveness and the generalization ability of our model.

We argue that chemistry should be the next grand challenge for Artificial Intelligence. The AI research community and humanity would benefit tremendously from focusing AI research on chemistry on a regular basis, as a benchmark as well as a real-world application domain. To support our position, we review the importance of chemical compound discovery and synthesis planning and discuss the properties of search spaces in a chemistry problem. Knowledge acquired in domains such as two-player board games or single-player puzzles places the AI community in a good position to solve critical problems in the chemistry domain. Yet, we show that searching in chemistry problems poses significant additional challenges that will have to be addressed. Finally, we envision how several AI areas like Natural Language Processing, Machine Learning, planning and search, are relevant for chemistry.

Video summarization aims to facilitate large-scale video browsing by producing short, concise summaries that are diverse and representative of original videos. In this paper, we formulate video summarization as a sequential decision-making process and develop a deep summarization network (DSN) to summarize videos. DSN predicts for each video frame a probability, which indicates how likely a frame is selected, and then takes actions based on the probability distributions to select frames, forming video summaries. To train our DSN, we propose an end-to-end, reinforcement learning-based framework, where we design a novel reward function that jointly accounts for diversity and representativeness of generated summaries and does not rely on labels or user interactions at all. During training, the reward function judges how diverse and representative the generated summaries are, while DSN strives for earning higher rewards by learning to produce more diverse and more representative summaries. Since labels are not required, our method can be fully unsupervised. Extensive experiments on two benchmark datasets show that our unsupervised method not only outperforms other state-of-the-art unsupervised methods, but also is comparable to or even superior than most of published supervised approaches.

In the research area of computer vision and artificial intelligence, learning the relationships of objects is an important way to deeply understand images. Most of recent works detect visual relationship by learning objects and predicates respectively in feature level, but the dependencies between objects and predicates have not been fully considered. In this paper, we introduce deep structured learning for visual relationship detection. Specifically, we propose a deep structured model, which learns relationship by using feature-level prediction and label-level prediction to improve learning ability of only using feature-level predication. The feature-level prediction learns relationship by discriminative features, and the label-level prediction learns relationships by capturing dependencies between objects and predicates based on the learnt relationship of feature level. Additionally, we use structured SVM (SSVM) loss function as our optimization goal, and decompose this goal into the subject, predicate, and object optimizations which become more simple and more independent. Our experiments on the Visual Relationship Detection (VRD) dataset and the large-scale Visual Genome (VG) dataset validate the effectiveness of our method, which outperforms state-of-the-art methods.

The potential for agents, whether embodied or software, to learn by observing other agents performing procedures involving objects and actions is rich. Current research on automatic procedure learning heavily relies on action labels or video subtitles, even during the evaluation phase, which makes them infeasible in real-world scenarios. This leads to our question: can the human-consensus structure of a procedure be learned from a large set of long, unconstrained videos (e.g., instructional videos from YouTube) with only visual evidence? To answer this question, we introduce the problem of procedure segmentation---to segment a video procedure into category-independent procedure segments. Given that no large-scale dataset is available for this problem, we collect a large-scale procedure segmentation dataset with procedure segments temporally localized and described; we use cooking videos and name the dataset YouCook2. We propose a segment-level recurrent network for generating procedure segments by modeling the dependencies across segments. The generated segments can be used as pre-processing for other tasks, such as dense video captioning and event parsing. We show in our experiments that the proposed model outperforms competitive baselines in procedure segmentation.

To have a more meaningful impact, educational applications need to significantly improve the way feedback is offered to teachers and students. We propose two methods for determining propositional-level entailment relations between a reference answer and a student's response. Both methods, one using hand-crafted features and an SVM and the other using word embeddings and deep neural networks, achieve significant improvements over a state-of-the-art system and two alternative approaches.