The MIT team first used the deep learning model to screen a library of 6,000 molecules for those which may be effective against E. coli. The search detected halicin, which the authors tested against a number of cultured bacterial strains, discovering the molecule "displays bactericidal activity against a wide phylogenetic spectrum of pathogens including Mycobacterium tuberculosis and carbapenem-resistant Enterobacteriaceae," the authors wrote. The researchers also found halicin kills C. difficile and a "pan-resistant" infection in mouse models. In a subsequent screen of more than 107 million molecules from the ZINC15 database provided by the University of California, San Francisco, the AI tool identified eight molecules with structures distinct from known antibiotics but which might have potent anti-bacterial properties. Professor Jacob Durrant of the University of Pittsburgh, a drug design researcher who was not part of the study, told The Guardian: "The work really is remarkable.

Natural language processing (NLP) is one of the most important technologies to arise in recent years. Specifically, 2019 has been a big year for NLP with the introduction of the revolutionary BERT language representation model. There are a large variety of underlying tasks and machine learning models powering NLP applications. Recently, deep learning approaches have obtained very high performance across many different NLP tasks. Convolutional Neural Network (CNNs) are typically associated with computer vision, but more recently CNNs have been applied to problems in NLP.

The open-source Anaconda Distribution is the easiest way to perform Python/R data science and machine learning on Linux, Windows, and Mac OS X.

Hive is a full-stack deep learning platform helping to bring companies into the AI era. We take complex visual challenges and build custom machine learning models to solve them. For AI to work, companies need large volumes of high quality training data. We generate this data through Hive Data, our proprietary data labeling platform with over 1,000,000 globally distributed workers, generating millions of high quality pieces of data per day. We then use this training data to build machine learning models for verticals such as Media, Autonomous Driving, Security, and Retail.

Tesla CEO Elon Musk wants to see all artificial intelligence better regulated, even at his own company, he tweeted Monday (via TechCrunch). He made the remark in response to a piece about OpenAI by MIT Technology Review, which claimed that the AI organization, co-founded by Musk, has shifted from its mission of developing and distributing AI safely and equitably into a secretive company obsessed with image and driven to constantly raise more money. Musk has a history of expressing serious concerns about the negative potential of AI. He tweeted in 2014 that it could be "more dangerous than nukes," and told an audience at an MIT Aeronautics and Astronautics symposium that year that AI was "our biggest existential threat," and humanity needs to be extremely careful: With artificial intelligence we are summoning the demon. In all those stories where there's the guy with the pentagram and the holy water, it's like yeah he's sure he can control the demon.

Elon Musk is calling for regulation on organizations developing advanced artificial intelligence, including his companies. The Tesla and SpaceX head tweeting earlier this week, "All orgs developing advanced AI should be regulated, including Tesla." Musk was, according to TechCrunch, "responding to a new MIT Technology Review profile of OpenAI, an organization founded in 2015 by Musk, along with Sam Altman, Ilya Sutskever, Greg Brockman, Wojciech Zaremba and John Schulman. Since 2015, Musk has distanced himself from OpenAI and openly criticized it. In a twitter conversation about the group last year, Musk tweeted, "Unfortunately, I must agree that these are reasonable concerns" when user @Smerity asked, "What is OpenAI?

We present an implementation of a probabilistic first-order logic called TensorLog, in which classes of logical queries are compiled into differentiable functions in a neural-network infrastructure such as Tensorflow or Theano. This leads to a close integration of probabilistic logical reasoning with deep-learning infrastructure: in particular, it enables high-performance deep learning frameworks to be used for tuning the parameters of a probabilistic logic. The integration with these frameworks enables use of GPU-based parallel processors for inference and learning, making TensorLog the first highly parallellizable probabilistic logic. Experimental results show that TensorLog scales to problems involving hundreds of thousands of knowledge-base triples and tens of thousands of examples.

Conventional relation extraction methods can only identify limited relation classes and not recognize the unseen relation types that have no pre-labeled training data. In this paper, we explore the zero-shot relation extraction to overcome the challenge. The only requisite information about unseen types is the name of their labels. We propose a Parasitic Neural Network (PNN), and it can learn a mapping between the general feature representations of text samples and the distributions of unseen types in a shared semantic space. Experiment results show that our model significantly outperforms others on the unseen relation extraction task and achieves effect improvement more than 20%, when there are not any manual annotations or additional resources.

In this paper, we present the submitted system for the second DIHARD Speech Diarization Challenge from the DKULENOVO team. Our diarization system includes multiple modules, namely voice activity detection (VAD), segmentation, speaker embedding extraction, similarity scoring, clustering, resegmentation and overlap detection. For each module, we explore different techniques to enhance performance. Our final submission employs the ResNet-LSTM based VAD, the Deep ResNet based speaker embedding, the LSTM based similarity scoring and spectral clustering. Variational Bayes (VB) diarization is applied in the resegmentation stage and overlap detection also brings slight improvement. Our proposed system achieves 18.84% DER in Track1 and 27.90% DER in Track2. Although our systems have reduced the DERs by 27.5% and 31.7% relatively against the official baselines, we believe that the diarization task is still very difficult.

Deep neural networks often consist of a great number of trainable parameters for extracting powerful features from given datasets. On one hand, massive trainable parameters significantly enhance the performance of these deep networks. On the other hand, they bring the problem of over-fitting. To this end, dropout based methods disable some elements in the output feature maps during the training phase for reducing the co-adaptation of neurons. Although the generalization ability of the resulting models can be enhanced by these approaches, the conventional binary dropout is not the optimal solution. Therefore, we investigate the empirical Rademacher complexity related to intermediate layers of deep neural networks and propose a feature distortion method (Disout) for addressing the aforementioned problem. In the training period, randomly selected elements in the feature maps will be replaced with specific values by exploiting the generalization error bound. The superiority of the proposed feature map distortion for producing deep neural network with higher testing performance is analyzed and demonstrated on several benchmark image datasets.