Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Abstract: Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.
Citations
More filters
TL;DR: Connections with another ML branch of reinforcement learning are elucidated and its role in control and decision problems is discussed, and implications of these advances for the fields of process and energy systems engineering are discussed.
252 citations
TL;DR: A comprehensive review of representative approaches for MCR and elaborate on their algorithmic details, computational costs, and how they fit into the PSP mapping problems is provided.
252 citations
TL;DR: The performance of DLR for predicting the mutation status of isocitrate dehydrogenase 1 (IDH1) was validated in a dataset of 151 patients with low-grade glioma and the AUC of IDH1 estimation was improved to 95% using DLR based on multiple-modality MR images, suggesting DLR could be a powerful way to extract deep information from medical images.
Abstract: Deep learning-based radiomics (DLR) was developed to extract deep information from multiple modalities of magnetic resonance (MR) images. The performance of DLR for predicting the mutation status of isocitrate dehydrogenase 1 (IDH1) was validated in a dataset of 151 patients with low-grade glioma. A modified convolutional neural network (CNN) structure with 6 convolutional layers and a fully connected layer with 4096 neurons was used to segment tumors. Instead of calculating image features from segmented images, as typically performed for normal radiomics approaches, image features were obtained by normalizing the information of the last convolutional layers of the CNN. Fisher vector was used to encode the CNN features from image slices of different sizes. High-throughput features with dimensionality greater than 1.6*104 were obtained from the CNN. Paired t-tests and F-scores were used to select CNN features that were able to discriminate IDH1. With the same dataset, the area under the operating characteristic curve (AUC) of the normal radiomics method was 86% for IDH1 estimation, whereas for DLR the AUC was 92%. The AUC of IDH1 estimation was further improved to 95% using DLR based on multiple-modality MR images. DLR could be a powerful way to extract deep information from medical images.
252 citations
TL;DR: It is demonstrated experimentally that the synaptic weights shared in different time steps in an LSTM can be implemented with a memristor crossbar array, which has a small circuit footprint, can store a large number of parameters and offers in-memory computing capability that contributes to circumventing the ‘von Neumann bottleneck’.
Abstract: Recent breakthroughs in recurrent deep neural networks with long short-term memory (LSTM) units have led to major advances in artificial intelligence. However, state-of-the-art LSTM models with significantly increased complexity and a large number of parameters have a bottleneck in computing power resulting from both limited memory capacity and limited data communication bandwidth. Here we demonstrate experimentally that the synaptic weights shared in different time steps in an LSTM can be implemented with a memristor crossbar array, which has a small circuit footprint, can store a large number of parameters and offers in-memory computing capability that contributes to circumventing the ‘von Neumann bottleneck’. We illustrate the capability of our crossbar system as a core component in solving real-world problems in regression and classification, which shows that memristor LSTM is a promising low-power and low-latency hardware platform for edge inference. Deep neural networks are increasingly popular in data-intensive applications, but are power-hungry. New types of computer chips that are suited to the task of deep learning, such as memristor arrays where data handling and computing take place within the same unit, are required. A well-used deep learning model called long short-term memory, which can handle temporal sequential data analysis, is now implemented in a memristor crossbar array, promising an energy-efficient and low-footprint deep learning platform.
251 citations
Cites background from "Deep learning"
...The recent success of artificial intelligence largely results from the advances of deep neural networks with various microstructures\cite{lecun2015nature}, among which long short- term memory (LSTM) is an important unit\cite{lstm1997,lstm2000}....
[...]
TL;DR: The CropDeep species classification and detection dataset, consisting of 31,147 images with over 49,000 annotated instances from 31 different classes, is presented and it is suggested that the YOLOv3 network has good potential application in agricultural detection tasks.
Abstract: Intelligence has been considered as the major challenge in promoting economic potential and production efficiency of precision agriculture. In order to apply advanced deep-learning technology to complete various agricultural tasks in online and offline ways, a large number of crop vision datasets with domain-specific annotation are urgently needed. To encourage further progress in challenging realistic agricultural conditions, we present the CropDeep species classification and detection dataset, consisting of 31,147 images with over 49,000 annotated instances from 31 different classes. In contrast to existing vision datasets, images were collected with different cameras and equipment in greenhouses, captured in a wide variety of situations. It features visually similar species and periodic changes with more representative annotations, which have supported a stronger benchmark for deep-learning-based classification and detection. To further verify the application prospect, we provide extensive baseline experiments using state-of-the-art deep-learning classification and detection models. Results show that current deep-learning-based methods achieve well performance in classification accuracy over 99%. While current deep-learning methods achieve only 92% detection accuracy, illustrating the difficulty of the dataset and improvement room of state-of-the-art deep-learning models when applied to crops production and management. Specifically, we suggest that the YOLOv3 network has good potential application in agricultural detection tasks.
251 citations
References
More filters
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Abstract: Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis of this problem, then address it by introducing a novel, efficient, gradient based method called long short-term memory (LSTM). Truncating the gradient where this does not do harm, LSTM can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Multiplicative gate units learn to open and close access to the constant error flow. LSTM is local in space and time; its computational complexity per time step and weight is O. 1. Our experiments with artificial data involve local, distributed, real-valued, and noisy pattern representations. In comparisons with real-time recurrent learning, back propagation through time, recurrent cascade correlation, Elman nets, and neural sequence chunking, LSTM leads to many more successful runs, and learns much faster. LSTM also solves complex, artificial long-time-lag tasks that have never been solved by previous recurrent network algorithms.
72,897 citations
01 Jan 1998
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Abstract: Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.
42,067 citations
TL;DR: Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.
Abstract: We describe a new learning procedure, back-propagation, for networks of neurone-like units. The procedure repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector. As a result of the weight adjustments, internal ‘hidden’ units which are not part of the input or output come to represent important features of the task domain, and the regularities in the task are captured by the interactions of these units. The ability to create useful new features distinguishes back-propagation from earlier, simpler methods such as the perceptron-convergence procedure1.
23,814 citations
TL;DR: This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
Abstract: The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
23,074 citations
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
Abstract: High-dimensional data can be converted to low-dimensional codes by training a multilayer neural network with a small central layer to reconstruct high-dimensional input vectors. Gradient descent can be used for fine-tuning the weights in such "autoencoder" networks, but this works well only if the initial weights are close to a good solution. We describe an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data.
16,717 citations