RNA-binding proteins (RBPs) play crucial roles in many biological processes, e.g. gene regulation. Computational identification of RBP binding sites on RNAs are urgently needed. In particular, RBPs bind to RNAs by recognizing sequence motifs. Thus, fast locating those motifs on RNA sequences is crucial and time-efficient for determining whether the RNAs interact with the RBPs or not. In this study, we present an attention based convolutional neural network, iDeepA, to predict RNA-protein binding sites from raw RNA sequences. We first encode RNA sequences into one-hot encoding. Next, we design a deep learning model with a convolutional neural network (CNN) and an attention mechanism, which automatically search for important positions, e.g. binding motifs, to learn discriminant high-level features for predicting RBP binding sites. We evaluate iDeepA on publicly gold-standard RBP binding sites derived from CLIP-seq data. The results demonstrate iDeepA achieves comparable performance with other state-of-the-art methods.

Over the last couple of years, deep learning and especially convolutional neural networks have become one of the work horses of computer vision. One limiting factor for the applicability of supervised deep learning to more areas is the need for large, manually labeled datasets. In this paper we propose an easy to implement method we call guided labeling, which automatically determines which samples from an unlabeled dataset should be labeled. We show that using this procedure, the amount of samples that need to be labeled is reduced considerably in comparison to labeling images arbitrarily.

A restricted Boltzmann machine (RBM) is an undirected graphical model constructed for discrete or continuous random variables, with two layers, one hidden and one visible, and no conditional dependency within a layer. In recent years, RBMs have risen to prominence due to their connection to deep learning. By treating a hidden layer of one RBM as the visible layer in a second RBM, a deep architecture can be created. RBMs are thought to thereby have the ability to encode very complex and rich structures in data, making them attractive for supervised learning. However, the generative behavior of RBMs is largely unexplored. In this paper, we discuss the relationship between RBM parameter specification in the binary case and model properties such as degeneracy, instability and uninterpretability. We also describe the difficulties that arise in likelihood-based and Bayes fitting of such (highly flexible) models, especially as Gibbs sampling (quasi-Bayes) methods are often advocated for the RBM model structure.

Biological plastic neural networks are systems of extraordinary computational capabilities shaped by evolution, development, and lifetime learning. The interplay of these elements leads to the emergence of adaptive behavior and intelligence. Inspired by such intricate natural phenomena, Evolved Plastic Artificial Neural Networks (EPANNs) use simulated evolution in-silico to breed plastic neural networks with a large variety of dynamics, architectures, and plasticity rules: these artificial systems are composed of inputs, outputs, and plastic components that change in response to experiences in an environment. These systems may autonomously discover novel adaptive algorithms, and lead to hypotheses on the emergence of biological adaptation. EPANNs have seen considerable progress over the last two decades. Current scientific and technological advances in artificial neural networks are now setting the conditions for radically new approaches and results. In particular, the limitations of hand-designed networks could be overcome by more flexible and innovative solutions. This paper brings together a variety of inspiring ideas that define the field of EPANNs. The main methods and results are reviewed. Finally, new opportunities and developments are presented.

Nvidia deep learning consultant Michelle Gill never imagined herself working in California's robot-crazed tech industry. When she left Nebraska and got a PhD in biochemistry and biophysics at Yale University, she saw herself as more of a scientist who studied life than a technologist prepared to build new creations. It wasn't until she started working at the National Cancer Institute that she first became interested in machine learning. Analyzing medical images with data science opened the door to a whole new world. "A lot of the concepts I had learned in science applied in some way to machine learning," Gill told Newsweek at the Artificial Intelligence & Data Science conference in New York City.

Publications like The Wall Street Journal, Forbes and Fortune have all called 2017 "The Year of AI." AI outperformed professional gamers and poker players in new realms. Access to deep learning education expanded through various online programs. The speech recognition accuracy record was broken multiple times, most recently by Microsoft. And research universities and organizations like Oxford, Massachusetts General Hospital and GE's Avitas Systems invested in deep learning supercomputers. These are a few of many milestones in 2017.

Scientists have created robot that can'see into their own future'. They use a technology called'visual foresight' that allows them to work out how to manipulate objects they have never encountered before. In the future, the technology could help self-driving cars anticipate events on the road and help produce more intelligent robotic assistants in homes. This new technology, called'visual foresight' means robots can work out how to manipulate objects they have never encountered before. The robot relies on a deep learning technology called dynamic neural advection (DNA).

Deep learning is a broad field of research with the objective of creating artificial intelligence that is capable of instructing itself to perform tasks rather than relying on algorithms. In theory, this would allow AI to succeed at tasks that would be prohibitively difficult, resource-intensive, or time-consuming for a human developer to work on. However, deep learning requires dedicated experts to oversee and develop the AI -- undermining some of the intent behind having AI that can self-teach. If you need an expert on hand regardless, why do you need an AI capable of deep learning? AWS and Microsoft seek to change that.

Simply put, training a deep learning model means that you're feeding data to the model, getting an output, and then using that output to make adjustments. For example, if you train your model on a bunch of pictures of cats and then feed it new cat photos it's never seen before, it should be able to pick out the cats in the new photos. If it doesn't, you can change the way the network's nodes are weighing certain characteristics of the images (the presence of whiskers and a tail, for instance). Weight, in this case, is a number that represents the importance of a characteristic. The higher the weight, the higher the influence that characteristic has on the nodes.

A lot of computational power is needed to solve deep learning problems because of the iterative nature of deep learning algorithms, their complexity as the number of layers increase, and the large volumes of data needed to train the networks. The dynamic nature of deep learning methods – their ability to continuously improve and adapt to changes in the underlying information pattern – presents a great opportunity to introduce more dynamic behavior into analytics. Greater personalization of customer analytics is one possibility. Another great opportunity is to improve accuracy and performance in applications where neural networks have been used for a long time. Through better algorithms and more computing power, we can add greater depth.