Spatial and time-dependent data is of interest in many applications. This task is difficult due to its complex spatial dependency, long-range temporal dependency, data non-stationarity, and data heterogeneity. To address these challenges, we propose Forecaster, a graph Transformer architecture. Specifically, we start by learning the structure of the graph that parsimoniously represents the spatial dependency between the data at different locations. Based on the topology of the graph, we sparsify the Transformer to account for the strength of spatial dependency, long-range temporal dependency, data non-stationarity, and data heterogeneity. We evaluate Forecaster in the problem of forecasting taxi ride-hailing demand and show that our proposed architecture significantly outperforms the state-of-the-art baselines.

Strong intelligent machines powered by deep neural networks are increasingly deployed as black boxes to make decisions in risk-sensitive domains, such as finance and medical. To reduce potential risk and build trust with users, it is critical to interpret how such machines make their decisions. Existing works interpret a pre-trained neural network by analyzing hidden neurons, mimicking pre-trained models or approximating local predictions. However, these methods do not provide a guarantee on the exactness and consistency of their interpretation. In this paper, we propose an elegant closed form solution named $OpenBox$ to compute exact and consistent interpretations for the family of Piecewise Linear Neural Networks (PLNN). The major idea is to first transform a PLNN into a mathematically equivalent set of linear classifiers, then interpret each linear classifier by the features that dominate its prediction. We further apply $OpenBox$ to demonstrate the effectiveness of non-negative and sparse constraints on improving the interpretability of PLNNs. The extensive experiments on both synthetic and real world data sets clearly demonstrate the exactness and consistency of our interpretation.

It is becoming increasingly clear that the big tech giants such as Google, Facebook, and Microsoft are extremely generous with their latest machine learning algorithms and packages (they give those away freely) because the entry barrier to the world of algorithms is pretty low right now. The open source community and tools (such as scikit-earn) have come a long way, and plenty of open source initiatives are propelling the vehicles of data science, digital analytics, and machine learning. Standing in 2019, we can safely say that algorithms, programming frameworks, and machine learning packages (or even tutorials and courses how to learn these techniques) are not the scarce resource but high-quality data is. This often becomes a thorny issue on the side of the practitioners in data science (DS) and machine learning (ML) when it comes to tweaking and fine-tuning those algorithms. It will also be wise to point out, at the very beginning, that the current article pertains to the scarcity of data for algorithmic investigation, pedagogical learning, and model prototyping.

Quite a mix of machine learning projects we have here. I have provided tutorials, guides and resources after each GitHub project. I have one ask – pick the project that interests you, go through the tutorial, and then apply that particular library to solve the problem. For example, you could take up the NeuralClassifier repository and use that to solve a multi-label classification problem. This will help you broaden your understanding of the topic and expand your current skillset.

Attention readers: We invite you to access the corresponding Python code and iPython notebooks for this article on GitHub. Given all of the higher level tools that you can use with TensorFlow, such as tf.contrib.learn But often with these higher level applications, you cannot access the little inbetween bits of the code, and some of the understanding of what's happening under the surface is lost. In this tutorial, I'll walk you through how to build a convolutional neural network from scratch, using just the low-level TensorFlow and visualizing our graph and network performance using TensorBoard. If you don't understand some of the basics of a fully connected neural network, I highly recommend you first check out Not another MNIST tutorial with TensorFlow.

In role-playing games (RPGs) such as the modern crime classic Grand Theft Auto, many players create their in-game characters based on their own appearance. Although today's built-in character customization systems are becoming increasingly sophisticated, they can involve tedious manual adjustments across dozens or even hundreds of parameters, which can take up to several hours to complete. A team of researchers from the Chinese gaming giant NetEase have developed a method to automatically create players' in-game characters from a standard portrait photo. They break down the details of their method the paper Face-to-Parameter Translation for Game Character Auto-Creation. The character generation process starts by aligning the human player's portrait photo, which is used as the training input for a deep learning-based framework comprising an imitator module and a feature extractor.

We developed CheXNeXt, a convolutional neural network to concurrently detect the presence of 14 different pathologies, including pneumonia, pleural effusion, pulmonary masses, and nodules in frontal-view chest radiographs. CheXNeXt was trained and internally validated on the ChestX-ray8 dataset, with a held-out validation set consisting of 420 images, sampled to contain at least 50 cases of each of the original pathology labels. On this validation set, the majority vote of a panel of 3 board-certified cardiothoracic specialist radiologists served as reference standard. We compared CheXNeXt's discriminative performance on the validation set to the performance of 9 radiologists using the area under the receiver operating characteristic curve (AUC). The radiologists included 6 board-certified radiologists (average experience 12 years, range 4–28 years) and 3 senior radiology residents, from 3 academic institutions.

Artificial intelligence is a trending technology from quite a few years now. You must have heard a lot about it in tech news and blogs. There are various predictions about the future of Artificial intelligence but have you ever been keen to about its initial stages? In contemporary times, AI along with its subsets machine learning and deep learning are ruling the innovations in the software industry market. In fact, the magic of AI is such that 41 percent of consumers are expecting that their life will change with AI in the future.

Artificial Intelligence and Machine Learning are becoming exponentially more popular in the business world – especially when used as tools to better meet business objectives. Through the process of deep learning neural networks, AI and ML have the ability to classify images. A common and highly effective approach to deep learning on small image datasets is to use a pre-trained network like VGG16 and RESNET. One can also build custom deep learning models for image classification. When implementing the right tools, we can empower our computers with the ability of recognition, where they can virtually distinguish images from one another.

Continuing on my #100DaysOfMLCode, these are some of the courses I'm following and recommend if you are interested in learning ML and DL. One of the most stunning statistics in the area of Machine Learning (ML) was released by Tractica. According to the company, ML will grow from its $1.4 billon value as at 2016 to $59.8 billion by 2025. That is some massive growth to be recorded in just under ten years. The interesting thing is, not many are taking advantage of this market yet.