This repository contains an op-for-op PyTorch reimplementation of Google's TensorFlow repository for the BERT model that was released together with the paper BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova. This implementation is provided with Google's pre-trained models, examples, notebooks and a command-line interface to load any pre-trained TensorFlow checkpoint for BERT is also provided. This repo was tested on Python 3.5 and PyTorch 0.4.1/1.0.0 A series of tests is included in the tests folder and can be run using pytest (install pytest if needed: pip install pytest). These examples are detailed in the Examples section of this readme.

Google AI's BERT paper shows the amazing result on various NLP task (new 17 NLP tasks SOTA), including outperform the human F1 score on SQuAD v1.1 QA task. This paper proved that Transformer(self-attention) based encoder can be powerfully used as alternative of previous language model with proper language model training method. And more importantly, they showed us that this pre-trained language model can be transfer into any NLP task without making task specific model architecture. This amazing result would be record in NLP history, and I expect many further papers about BERT will be published very soon. Code is very simple and easy to understand fastly.

Recurrent Neural Networks – Main use of RNNs are when using google or facebook these interfaces are able to predict next word what you are about to type. RNNs have loops to allow information to persist. RNN's are considered to be fairly good for modeling sequence data. Recurrent neural networks are linear architectural variant of recursive networks. This post is a high level over view for creating basic understanding.

This page provides resources about image similarity using deep learning, Siamese network, one-shot learning. There are several ways to compute image similarity with deep learning. One can either train an end to end deep model which learns similarity between images, or use the Deep model as a feature extractor and then use a standard similarity metric (Dot product, L2 distance etc.) It depends on the problem domain at hand. For example, if these are natural images with scenes/objects, one can use a pre-trained deep model (say, a GoogleNet model trained on ImageNet or maybe Natural scene images (like, say Places-205) and then extract features from one of the last few layers (either fc6 or fc7).

Social media are nowadays one of the main news sources for millions of people around the globe due to their low cost, easy access and rapid dissemination. This however comes at the cost of dubious trustworthiness and significant risk of exposure to 'fake news', intentionally written to mislead the readers. Automatically detecting fake news poses challenges that defy existing content-based analysis approaches. One of the main reasons is that often the interpretation of the news requires the knowledge of political or social context or 'common sense', which current NLP algorithms are still missing. Recent studies have shown that fake and real news spread differently on social media, forming propagation patterns that could be harnessed for the automatic fake news detection. Propagation-based approaches have multiple advantages compared to their content-based counterparts, among which is language independence and better resilience to adversarial attacks. In this paper we show a novel automatic fake news detection model based on geometric deep learning. The underlying core algorithms are a generalization of classical CNNs to graphs, allowing the fusion of heterogeneous data such as content, user profile and activity, social graph, and news propagation. Our model was trained and tested on news stories, verified by professional fact-checking organizations, that were spread on Twitter. Our experiments indicate that social network structure and propagation are important features allowing highly accurate (92.7% ROC AUC) fake news detection. Second, we observe that fake news can be reliably detected at an early stage, after just a few hours of propagation. Third, we test the aging of our model on training and testing data separated in time. Our results point to the promise of propagation-based approaches for fake news detection as an alternative or complementary strategy to content-based approaches.

Deep reinforcement learning provides a promising approach for vision-based control of real-world robots. However, the generalization of such models depends critically on the quantity and variety of data available for training. This data can be difficult to obtain for some types of robotic systems, such as fragile, small-scale quadrotors. Simulated rendering and physics can provide for much larger datasets, but such data is inherently of lower quality: many of the phenomena that make the real-world autonomous flight problem challenging, such as complex physics and air currents, are modeled poorly or not at all, and the systematic differences between simulation and the real world are typically impossible to eliminate. In this work, we investigate how data from both simulation and the real world can be combined in a hybrid deep reinforcement learning algorithm. Our method uses real-world data to learn about the dynamics of the system, and simulated data to learn a generalizable perception system that can enable the robot to avoid collisions using only a monocular camera. We demonstrate our approach on a real-world nano aerial vehicle collision avoidance task, showing that with only an hour of real-world data, the quadrotor can avoid collisions in new environments with various lighting conditions and geometry. Code, instructions for building the aerial vehicles, and videos of the experiments can be found at github.com/gkahn13/GtS

This paper presents an extension and an elaboration of the theory of differential similarity, which was originally proposed in arXiv:1401.2411 [cs.LG]. The goal is to develop an algorithm for clustering and coding that combines a geometric model with a probabilistic model in a principled way. For simplicity, the geometric model in the earlier paper was restricted to the three-dimensional case. The present paper removes this restriction, and considers the full $n$-dimensional case. Although the mathematical model is the same, the strategies for computing solutions in the $n$-dimensional case are different, and one of the main purposes of this paper is to develop and analyze these strategies. Another main purpose is to devise techniques for estimating the parameters of the model from sample data, again in $n$ dimensions. We evaluate the solution strategies and the estimation techniques by applying them to two familiar real-world examples: the classical MNIST dataset and the CIFAR-10 dataset.

Convolutional Neural Networks (CNNs) are successfully used for the important automotive visual perception tasks including object recognition, motion and depth estimation, visual SLAM, etc. However, these tasks are independently explored and modeled. In this paper, we propose a joint multi-task network design called NeurAll for learning all tasks simultaneously. Our main motivation is the computational efficiency achieved by sharing the expensive initial convolutional layers between all tasks. Indeed, the main bottleneck in automated driving systems is the limited processing power available on deployment hardware. There could be other benefits in improving accuracy for some tasks and it eases development effort. It also offers scalability to add more tasks leveraging existing features and achieving better generalization. We survey various CNN based solutions for visual perception tasks in automated driving. Then we propose a unified CNN model for the important tasks and discuss several advanced optimization and architecture design techniques to improve the baseline model. The paper is partly review and partly positional with demonstration of several preliminary results promising for future research. Firstly, we show that an efficient two-task model performing semantic segmentation and object detection achieves similar accuracies compared to separate models on various datasets with minimized runtime. We then illustrate that using depth regression as auxiliary task improves semantic segmentation and using multi-stream semantic segmentation outperforms one-stream semantic segmentation. The two-task network achieves 30 fps on an automotive grade low power SOC for 1280x384 image resolution

We introduce a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function defined over those labels, we process images through a "probe network" and compute an embedding based on estimates of the Fisher information matrix associated with the probe network parameters. This provides a fixed-dimensional embedding of the task that is independent of details such as the number of classes and does not require any understanding of the class label semantics. We demonstrate that this embedding is capable of predicting task similarities that match our intuition about semantic and taxonomic relations between different visual tasks (e.g., tasks based on classifying different types of plants are similar) We also demonstrate the practical value of this framework for the meta-task of selecting a pre-trained feature extractor for a new task. We present a simple meta-learning framework for learning a metric on embeddings that is capable of predicting which feature extractors will perform well. Selecting a feature extractor with task embedding obtains a performance close to the best available feature extractor, while costing substantially less than exhaustively training and evaluating on all available feature extractors.

While physics conveys knowledge of nature built from an interplay between observations and theory, it has been considered less importantly in deep neural networks. Especially, there are few works leveraging physics behaviors when the knowledge is given less explicitly. In this work, we propose a novel architecture called Differentiable Physics-informed Graph Networks (DPGN) to incorporate implicit physics knowledge which is given from domain experts by informing it in latent space. Using the concept of DPGN, we demonstrate that climate prediction tasks are significantly improved. Besides the experiment results, we validate the effectiveness of the proposed module and provide further applications of DPGN, such as inductive learning and multistep predictions.