Over the past several years there has been a lot of buzz about blockchain. Many of the major technology-focused research organizations and their analysts have penned articles about what blockchain may or not become.

In this course we are going to look at advanced NLP. Previously, you learned about some of the basics, like how many NLP problems are just regular machine learning and data science problems in disguise, and simple, practical methods like bag-of-words and term-document matrices. These allowed us to do some pretty cool things, like detect spam emails, write poetry, spin articles, and group together similar words. In this course I'm going to show you how to do even more awesome things. We'll learn not just 1, but 4 new architectures in this course.

This course is the next logical step in my deep learning, data science, and machine learning series. I've done a lot of courses about deep learning, and I just released a course about unsupervised learning, where I talked about clustering and density estimation. So what do you get when you put these 2 together? In these course we'll start with some very basic stuff - principal components analysis (PCA), and a popular nonlinear dimensionality reduction technique known as t-SNE (t-distributed stochastic neighbor embedding). Next, we'll look at a special type of unsupervised neural network called the autoencoder.

Machine learning, task automation and robotics are already widely used in business. These and other AI technologies are about to multiply, and we look at how organizations can best take advantage of them. In the movie "2001" I found the scariest moment was when astronauts David Bowman and Frank Poole met in the EVA pod to discuss the artificially intelligent HAL 9000 computer's behavior -- and HAL reads their lips. In the paper Lip Reading Sentences in the Wild, researchers Joon Son Chung, of Oxford University, Andrew Senior, Oriol Vinyals, and Andrew Zisserman, of Google, tested an algorithm that bested professional human lip readers. Soon, surveillance videos may not only show your actions, but the content of your speech.

Detecting and segmenting salient objects in natural scenes, often referred to as salient object detection, has attracted a lot of interest in computer vision. While many models have been proposed and several applications have emerged, yet a deep understanding of achievements and issues is lacking. We aim to provide a comprehensive review of the recent progress in salient object detection and situate this field among other closely related areas such as generic scene segmentation, object proposal generation, and saliency for fixation prediction. Covering 228 publications, we survey i) roots, key concepts, and tasks, ii) core techniques and main modeling trends, and iii) datasets and evaluation metrics in salient object detection. We also discuss open problems such as evaluation metrics and dataset bias in model performance and suggest future research directions.

In this paper, we propose a probabilistic parsing model that defines a proper conditional probability distribution over non-projective dependency trees for a given sentence, using neural representations as inputs. The neural network architecture is based on bidirectional LSTM-CNNs, which automatically benefits from both word-and character-level representations, by using a combination of bidirectional LSTMs and CNNs. On top of the neural network, we introduce a probabilistic structured layer, defining a conditional log-linear model over non-projective trees. By exploiting Kirchhoff's Matrix-Tree Theorem (Tutte, 1984), the partition functions and marginals can be computed efficiently, leading to a straightforward end-to-end model training procedure via back-propagation. We evaluate our model on 17 different datasets, across 14 different languages. Our parser achieves state-of-the-art parsing performance on nine datasets.

When it comes to artificial intelligence (AI), perhaps very few people can claim they fathered a huge part of it. One such man is Jürgen Schmidhuber. Schmidhuber is considered the"father of very deep learning," and the pioneer of deep learning neural networks. In fact, he built the foundations for many of the AI systems we find in our smartphones today. If anyone can predict how far AI will go in the next couple years, it's him. During a talk at WIRED2016, Schmidhuber presented the future of AI as something beyond just taking over jobs.

Originally posted on The Horizons Tracker. I've looked before at the growing role AI is playing in the development of new medicines, whether it's understanding which compounds to test, or even in the creation of virtual models to test drugs in. At the forefront of this trend is Insilico Medicine, who you may remember I wrote about recently after they'd developed a system that can guess your age accurately just by looking at you. They have certainly been busy, and recently published a paper looking at the role of deep learning in predicting the impact drugs might have on the body. The study saw a neural network trained up to predict the therapeutic use of a huge array of drugs.

This is a guide to the main differences I've found between PyTorch and TensorFlow. This post is intended to be useful for anyone considering starting a new project or making the switch from one deep learning framework to another. The focus is on programmability and flexibility when setting up the components of the training and deployment deep learning stack. PyTorch is better for rapid prototyping in research, for hobbyists and for small scale projects. TensorFlow is better for large-scale deployments, especially when cross-platform and embedded deployment is a consideration.