Automatic text summarization (ATS) has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale corpora. To make the summarization results more faithful, this paper presents an unsupervised approach that combines rhetorical structure theory, deep neural model and domain knowledge concern for ATS. This architecture mainly contains three components: domain knowledge base construction based on representation learning, attentional encoder-decoder model for rhetorical parsing and subroutine-based model for text summarization. Domain knowledge can be effectively used for unsupervised rhetorical parsing thus rhetorical structure trees for each document can be derived. In the unsupervised rhetorical parsing module, the idea of translation was adopted to alleviate the problem of data scarcity. The subroutine-based summarization model purely depends on the derived rhetorical structure trees and can generate content-balanced results. To evaluate the summary results without golden standard, we proposed an unsupervised evaluation metric, whose hyper-parameters were tuned by supervised learning. Experimental results show that, on a large-scale Chinese dataset, our proposed approach can obtain comparable performances compared with existing methods.

Click here to get the book.

I've been searching for a while now to find the precise way to feed a Recurrent Neural Network (RNN, LSTM, GRU, ESN, Etc) with time series data with no real success. Here is a question that was close, but the answers aren't very clear: Proper way of using recurrent neural network for time series analysis I'm not looking for a breakdown of how the networks work, but rather how to structure the input/output vectors for optimal results. So, let's say I'm working with a growing sinusoid. I am very familiar with the sliding time window approach that works well with Feed forward networks (FFN). And this works very well with FFN (And with RNN also), but I'm led to believe RNN shouldn't need to be setup that way. Rather they work very well with time series data and all I should need need to do is have the input be the previous output.

It's (mostly) powered by OpenAI's GPT-2 and has additional fine-tuned models: The main technical challenges were creating an app that could deliver OpenAI's GPT-2 Medium (a ml model that generates text) quickly and simultaneously support 10-20 heavy users. Above steps had to be fully automated or scaling failed. It feels dirty (in 2019) to write bash scripts as part of an automated deployment, but it's necessary when using autoscaling on Google startup-scripts. Kubernetes is another option, but I'm not smart enough to use K8. Google startup-scripts runs a shell script when the machine starts.

Word on the street is that Tesla has now equipped its ever-growing tech-arsenal in the form of DeepScale. This UC Berkeley computer vision startup has proved their mettle last year with their work on SqueezeNet and Carver 21. The news of this acquisition was followed by DeepScale CEO's Forrest Iandola post on social media announcing his association with Tesla as a senior staff machine learning scientist. I joined the @Tesla #Autopilot team this week. I am looking forward to working with some of the brightest minds in #deeplearning and #autonomousdriving.

The paper presented at ICLR 2019 can be found here. I also have slides as well as a poster explaining the work in detail. Deep neural networks are an amazing piece of technology. With enough labelled data they can learn to produce very accurate classifiers for high dimensional input such as images and sound. In recent years the machine learning community has been able to successfully tackle problems such as classifying objects, detecting objects in images and segmenting images.

Would you like to rate it again? Marcus is an awkward boy in high school who is in love with a girl named Kim who is not what she initially seems! Follow him and his low self-esteem adventures in high school!

If you've shopped in the online world, you've encountered recommendation engines. These artificial intelligence (AI) systems, also known as recommendation systems or recommender systems, leverage algorithms that help users find products and services based on their past buying behaviors, known preferences and more. Through their ability to predict interests and desires at a personalized level, recommendation engines help content and product providers drive people to music, video, books, clothes and just about any other product or service they might be interested in. Services like Amazon, Netflix, Spotify and YouTube make heavy use of recommendation engines in an effort to increase sales and improve customer satisfaction. Best Buy has some recommendations tailored to your tastes.

AI systems have an endless appetite for data. For an autonomous car's camera to identify pedestrians every time -- not just nearly every time -- its software needs to have studied countless examples of people standing, walking and running near roads. Yes, but: Gathering and labeling those images is expensive and time consuming, and in some cases impossible. So companies are teaching AI systems with fake photos and videos, sometimes also generated by AI, that stand in for the real thing.

Artificial intelligence seems to be everywhere these days. The news has stories about poetry-writing AI, the experts consider AI "the new electricity" and even AI whiskey is going to make an appearance soon. When you try reading these articles, there's usually a flood of information coming at you. But what do these concepts even mean? With this series of blog posts, we're going to address all the questions you've ever had about this topic and take you on an amazing adventure. In this first part, we're going to introduce the concepts of machine learning, neural networks, and deep learning. You don't need any previous knowledge about these topics to follow this article, so settle in and keep reading! Let's start with a basic concept: functions.