activities
recruitment
topics
open CSDN APP
Copyright? 1999-22, CSDN.NET , All Rights Reserved
Search for blog posts/users
Log in
Old birds who like soy sauce
Pay attention to
Analysis of the development trend of deep learning technology reprinted
219-4-9 8:37:11
1 Like
Old birds who like soy sauce
. FtIhKiENv483iHE53RPkg
At present, the development of artificial intelligence has been fully concerned and promoted by the breakthrough of deep learning technology, and governments all over the world attach great importance to it, and the capital boom is still overweight, and all walks of life have reached a consensus that it has become a hot spot for development. This paper aims to analyze the current situation of deep learning technology, judge the development trend of deep learning, and put forward development suggestions according to the technical level of our country.
First, the status quo of deep learning technology
Deep learning is the key technology of this round of artificial intelligence explosion. The breakthrough of artificial intelligence technology in computer vision and natural language processing has ushered in a new round of explosive development of artificial intelligence. And deep learning is the key technology to achieve these breakthroughs. Among them, the image classification technology based on deep convolution network has exceeded the accuracy of human eyes, the speech recognition technology based on deep neural network has reached 95% accuracy, and the machine translation technology based on deep neural network has approached the average translation level of human beings. The great improvement of accuracy makes computer vision and natural language processing enter the stage of industrialization, which brings the rise of new industries.
deep learning is an algorithm weapon in the era of big data, and it has become a research hotspot in recent years. Compared with the traditional machine learning algorithm, deep learning technology has two advantages. First, deep learning technology can continuously improve its performance with the increase of data scale, while traditional machine learning algorithms are difficult to continuously improve its performance by using massive data. Second, deep learning technology can directly extract features from data, which reduces the work of designing feature extractors for each problem, while traditional machine learning algorithms need to extract features manually. Therefore, deep learning has become a hot technology in the era of big data, and both academia and industry have carried out a lot of research and practical work on deep learning.
various models of deep learning fully empower basic applications. Convolutional neural network and cyclic neural network are two widely used deep neural network models. Computer vision and natural language processing are two basic applications of artificial intelligence. Convolutional neural network is widely used in the field of computer vision, and its performance in image classification, object detection, semantic segmentation and other tasks greatly exceeds that of traditional methods. Cyclic neural network is suitable for solving the problems related to sequence information, and has been widely used in the field of natural language processing, such as speech recognition, machine translation, dialogue system and so on.
Second, the development trend of deep learning
Deep neural networks show the development trend of deeper layers and more complex structures. In order to continuously improve the performance of deep neural network, the industry continues to explore from two aspects: network depth and network structure. The number of layers of neural network has expanded to hundreds or even thousands of layers. With the deepening of the number of layers of network, its learning effect is getting better and better. In 215, ResNet proposed by Microsoft exceeded the accuracy of image classification tasks for the first time with a network depth of 152 layers. New network design structures are constantly proposed, which makes the structure of neural network more and more complex. For example, in 214, Google proposed an Inception network structure, in 215, Microsoft proposed a residual network structure, and in 216, Huang Gao and others proposed a dense connection network structure. These network structure designs have continuously improved the performance of deep neural networks.
the functions of deep neural network nodes are constantly enriched. In order to overcome the limitations of the current neural network, the industry has explored and proposed a new type of neural network node, which makes the functions of the neural network more and more abundant. In 217, Jeffrey? Hinton put forward the concept of capsule network, which uses capsules as network nodes, which is closer to the behavior of human brain in theory, in order to overcome the limitations of convolutional neural networks, such as lack of spatial stratification and reasoning ability. In 218, scholars from DeepMind, Google Brain and MIT jointly put forward the concept of graph network, and defined a new class of modules with the function of relationship induction bias, aiming at giving deep learning the ability of causal reasoning.
the engineering application technology of deep neural network is deepening. Most of the deep neural network models have hundreds of millions of parameters and hundreds of megabytes of occupied space, so it is difficult to deploy them to terminal devices with limited performance and resources such as smart phones, cameras and wearable devices. In order to solve this problem, the industry adopts model compression technology to reduce the parameters and size of the model and reduce the amount of calculation. At present, the model compression methods used include pruning the trained model (such as pruning, weight sharing and quantization, etc.) and designing more elaborate models (such as MobileNet, etc.). The modeling and parameter adjustment process of deep learning algorithm is complicated and the application threshold is high. In order to lower the application threshold of deep learning, the industry has put forward the technology of Automatic Machine Learning (AutoML), which can realize the automatic design of deep neural network and simplify the use process.