Topic Tag: DNN

home Forums Topic Tag: DNN

 Understanding the Logical and Semantic Structure of Large Documents

 

Current language understanding approaches focus on small documents, such as newswire articles, blog posts, product reviews and discussion forum entries. Understanding and extracting information from large documents like legal briefs, proposals, technical manuals and research articles is still a cha…


 Deep Reinforcement Learning: An Overview

      

We give an overview of recent exciting achievements of deep reinforcement learning (RL). We discuss six core elements, six important mechanisms, and twelve applications. We start with background of machine learning, deep learning and reinforcement learning. Next we discuss core RL elements, includi…


 Grasping the Finer Point: A Supervised Similarity Network for Metaphor Detection

 

The ubiquity of metaphor in our everyday communication makes it an important problem for natural language understanding. Yet, the majority of metaphor processing systems to date rely on hand-engineered features and there is still no consensus in the field as to which features are optimal for this t…


 Robustly representing inferential uncertainty in deep neural networks through sampling

    

As deep neural networks (DNNs) are applied to increasingly challenging problems, they will need to be able to represent their own uncertainty. Modelling uncertainty is one of the key features of Bayesian methods. Using Bernoulli dropout with sampling at prediction time has recently been proposed as…


 Model based learning for accelerated, limited-view 3D photoacoustic tomography

  

Recent advances in deep learning for tomographic reconstructions have shown great potential to create accurate and high quality images with a considerable speed-up. In this work we present a deep neural network that is specifically designed to provide high resolution 3D images from restricted photo…


 A Deep Learning Approach for Population Estimation from Satellite Imagery

  

Knowing where people live is a fundamental component of many decision making processes such as urban development, infectious disease containment, evacuation planning, risk management, conservation planning, and more. While bottom-up, survey driven censuses can provide a comprehensive view into the …


 DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars

 

Recent advances in Deep Neural Networks (DNNs) have led to the development of DNN-driven autonomous cars that, using sensors like camera, LiDAR, etc., can drive without any human intervention. Most major manufacturers including Tesla, GM, Ford, BMW, and Waymo/Google are working on building and test…


 A parameterized activation function for learning fuzzy logic operations in deep neural networks

 

We present a deep learning architecture for learning fuzzy logic expressions. Our model uses an innovative, parameterized, differentiable activation function that can learn a number of logical operations by gradient descent. This activation function allows a neural network to determine the relation…


 Deep learning with convolutional neural networks for decoding and visualization of EEG pathology

  

We apply convolutional neural networks (ConvNets) to the task of distinguishing pathological from normal EEG recordings in the Temple University Hospital EEG Abnormal Corpus. We use two basic, shallow and deep ConvNet architectures recently shown to decode task-related information from EEG at least…


 TraNNsformer: Neural Network Transformation for Memristive Crossbar based Neuromorphic System Design

Implementation of Neuromorphic Systems using post Complementary Metal-Oxide-Semiconductor (CMOS) technology based Memristive Crossbar Array (MCA) has emerged as a promising solution to enable low-power acceleration of neural networks. However, the recent trend to design Deep Neural Networks (DNNs) …


 Phonetic Temporal Neural Model for Language Identification

  

Deep neural models, particularly the LSTM-RNN model, have shown great potential for language identification (LID). However, the use of phonetic information has been largely overlooked by most existing neural LID methods, although this information has been used very successfully in conventional phon…


 Supervised Speech Separation Based on Deep Learning: An Overview

 

Speech separation is the task of separating target speech from background interference. Traditionally, speech separation is studied as a signal processing problem. A more recent approach formulates speech separation as a supervised learning problem, where the discriminative patterns of speech, spea…


 Launching the Speech Commands Dataset

    

Posted by Pete Warden, Software Engineer, Google Brain Team At Google, we’re often asked how to get started using deep learning for speech and other audio recognition problems, like detecting keywords or commands. And while there are some great open source speech recognition systems like Kaldi th…


 DelugeNets: Deep Networks with Efficient and Flexible Cross-layer Information Inflows

  

Deluge Networks (DelugeNets) are deep neural networks which efficiently facilitate massive cross-layer information inflows from preceding layers to succeeding layers. The connections between layers in DelugeNets are established through cross-layer depthwise convolutional layers with learnable filte…


 Expressions in Virtual Reality

   

Posted by Steven Hickson, Software Engineering Intern, and Nick Dufour, Avneesh Sud, Software Engineers, Machine Perception Recently Google Machine Perception researchers, in collaboration with Daydream Labs and YouTube Spaces, presented a solution for virtual headset ‘removal’ for mixed realit…


 Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detection

 

The problem of cross-platform binary code similarity detection aims at detecting whether two binary functions coming from different platforms are similar or not. It has many security applications, including plagiarism detection, malware detection, vulnerability search, etc. Existing approaches rely…


 Phoenix: A Self-Optimizing Chess Engine

  

Since the advent of computers, many tasks which required humans to spend a lot of time and energy have been trivialized by the computers’ ability to perform repetitive tasks extremely quickly. Playing chess is one such task. It was one of the first games which was `solved’ using AI. Wit…


 Pillar Networks++: Distributed non-parametric deep and wide networks

     

In recent work, it was shown that combining multi-kernel based support vector machines (SVMs) can lead to near state-of-the-art performance on an action recognition dataset (HMDB-51 dataset). This was 0.4% lower than frameworks that used hand-crafted features in addition to the deep convolutional f…


 Building Your Own Neural Machine Translation System in TensorFlow

   

Posted by Thang Luong, Research Scientist, and Eugene Brevdo, Staff Software Engineer, Google Brain Team Machine translation – the task of automatically translating between languages – is one of the most active research areas in the machine learning community. Among the many approaches to machi…


 Faster Physics in Python

We’re open-sourcing a high-performance Python library for robotic simulation using the MuJoCo engine, developed over our past year of robotics research. View CodeView Docs This library is one of our core tools for deep learning robotics research, which we’ve now released as a major ver…


 Interpreting Deep Neural Networks using Cognitive Psychology

Interpreting Deep Neural Networks using Cognitive Psychology by DeepMind


 Explained: Neural networks

Ballyhooed artificial-intelligence technique known as “deep learning” revives 70-year-old idea. Explained: Neural networks by Larry Hardesty | MIT News Office