Scientists have built neural networks from DNA molecules that can recognise handwritten numbers, a common task in deep learning, according to a paper published in Nature on Wednesday. Now, scientists are testing wackier models on the MNIST database of training images, like one network modeled on moth brains or made out of DNA. Researchers at the California Institute of Technology have strung together nucleotides to create molecular logic gates. "Humans each have over 80 billion neurons in the brain, with which they make highly sophisticated decisions. Smaller animals such as roundworms can make simpler decisions using just a few hundred neurons," said Lulu Qian, co-author of the paper and an assistant professor in bioengineering at Caltech.

Those among us who fear that we've already passed the point of no return when it comes to artificial intelligence becoming self-aware and plotting to murder the human race will likely cite A.I. research company DeepMind's latest experiment as further proof of that notion. Using Id Software's Quake III Arena, DeepMind has managed to train artificial players to be even more effective than their human counterparts. The challenge for DeepMind was not to see if its A.I. agents could defeat human players in battle, but rather if they could work together on procedurally generated levels to complete an objective -- in this case, capture the flag. Because the levels' structure changes each time they play, the agents are unable to simply memorize locations in order to make it to the flag. This forced them to actually learn the strategies needed to win in a similar manner to how human players might improve at the game.

DeepMind, an Alphabet subsidiary, announced Tuesday its efforts to create an artificial intelligence (AI) that functions with human-like performance. Using Quake III Arena's Capture the Flag (CTF), a 3D first-person multiplayer video game, DeepMind taught AI how to work with and against humans to win the game. The rules of CTF haven't changed much since gym class. Two groups of individuals band together to steal the opponent's flag from their territory while also protecting their own. Teams can tag opponents that enter their territory, sending them back to their respective home base.

Children with autism spectrum conditions often have trouble recognizing the emotional states of people around them -- distinguishing a happy face from a fearful face, for instance. To remedy this, some therapists use a kid-friendly robot to demonstrate those emotions and to engage the children in imitating the emotions and responding to them in appropriate ways. This type of therapy works best, however, if the robot can smoothly interpret the child's own behavior -- whether he or she is interested and excited or paying attention -- during the therapy. Researchers at the MIT Media Lab have now developed a type of personalized machine learning that helps robots estimate the engagement and interest of each child during these interactions, using data that are unique to that child. Armed with this personalized "deep learning" network, the robots' perception of the children's responses agreed with assessments by human experts, with a correlation score of 60 percent, the scientists report June 27 in Science Robotics.

Over the last years, companies have reaped the benefits of embracing data-driven methods. The data 2.0 strategy will be driven by new AI techniques like deep learning, reinforcement learning, and Bayesian machine learning. Deep learning is the state-of-the-art approach to AI across machine translation, computer vision, and natural language processing. Not using these techniques hurts bottom lines and limits the end-user experience. Approaches using deep learning, solve problems end-to-end.

IMAGE: Insilico Medicine developed a novel deep-learning based model that predicts a biological age of a muscle. Thursday, July 5th, Rockville, MD - Insilico Medicine, a Rockville-based next-generation artificial intelligence company specializing in the application of deep learning for target identification, drug discovery and aging research announces the publication of a new research paper "Machine learning on human muscle transcriptomic data for biomarker discovery and tissue-specific drug target identification" in Frontiers in Genetics journal. Sarcopenia (from Greek "flesh poverty"), is one of the major age-related processes and involves the loss of skeletal muscle and its function. Age-associated muscle wasting remains an important clinical challenge that impacts hundreds of millions of older adults. It is associated with serious negative health outcomes such as falls, impaired standing balance, physical disability, and mortality.

With rise of digital age, there is an explosion of information in the form of news, articles, social media, and so on. Much of this data lies in unstructured form and manually managing and effectively making use of it is tedious, boring and labor intensive. This explosion of information and need for more sophisticated and efficient information handling tools gives rise to Information Extraction(IE) and Information Retrieval(IR) technology. Information Extraction systems takes natural language text as input and produces structured information specified by certain criteria, that is relevant to a particular application. Various sub-tasks of IE such as Named Entity Recognition, Coreference Resolution, Named Entity Linking, Relation Extraction, Knowledge Base reasoning forms the building blocks of various high end Natural Language Processing (NLP) tasks such as Machine Translation, Question-Answering System, Natural Language Understanding, Text Summarization and Digital Assistants like Siri, Cortana and Google Now. This paper introduces Information Extraction technology, its various sub-tasks, highlights state-of-the-art research in various IE subtasks, current challenges and future research directions.

In early years, text classification is typically accomplished by feature-based machine learning models; recently, deep neural networks, as a powerful learning machine, make it possible to work with raw input as the text stands. However, exiting end-to-end neural networks lack explicit interpretation of the prediction. In this paper, we propose a novel framework, JUMPER, inspired by the cognitive process of text reading, that models text classification as a sequential decision process. Basically, JUMPER is a neural system that scans a piece of text sequentially and makes classification decisions at the time it wishes. Both the classification result and when to make the classification are part of the decision process, which is controlled by a policy network and trained with reinforcement learning. Experimental results show that a properly trained JUMPER has the following properties: (1) It can make decisions whenever the evidence is enough, therefore reducing total text reading by 30-40% and often finding the key rationale of prediction. (2) It achieves classification accuracy better than or comparable to state-of-the-art models in several benchmark and industrial datasets.

We describe a novel weakly supervised deep learning framework that combines both the discriminative and generative models to learn meaningful representation in the multiple instance learning (MIL) setting. MIL is a weakly supervised learning problem where labels are associated with groups of instances (referred as bags) instead of individual instances. To address the essential challenge in MIL problems raised from the uncertainty of positive instances label, we use a discriminative model regularized by variational autoencoders (VAEs) to maximize the differences between latent representations of all instances and negative instances. As a result, the hidden layer of the variational autoencoder learns meaningful representation. This representation can effectively be used for MIL problems as illustrated by better performance on the standard benchmark datasets comparing to the state-of-the-art approaches. More importantly, unlike most related studies, the proposed framework can be easily scaled to large dataset problems, as illustrated by the audio event detection and segmentation task. Visualization also confirms the effectiveness of the latent representation in discriminating positive and negative classes.

Joint models for longitudinal and time-to-event data are commonly used in longitudinal studies to forecast disease trajectories over time. Despite the many advantages of joint modeling, the standard forms suffer from limitations that arise from a fixed model specification and computational difficulties when applied to large datasets. We adopt a deep learning approach to address these limitations, enhancing existing methods with the flexibility and scalability of deep neural networks while retaining the benefits of joint modeling. Using data from the Alzheimer's Disease Neuroimaging Institute, we show improvements in performance and scalability compared to traditional methods.