Shulou(Shulou.com)06/02 Report--

Deep learning (Deep Learning) is a kind of machine learning, and machine learning is the only way to realize artificial intelligence.

At present, most of the excellent AI applications use deep learning technology, leading the third wave of artificial intelligence.

one。 The concept of deep learning

Deep learning is a method based on representation of data in machine learning.

It belongs to the category of machine learning, which can be said to be an upgrade based on the traditional neural network, which is about equal to the neural network. Its advantage is to use unsupervised or semi-supervised feature learning and hierarchical feature extraction efficient algorithm to replace manual feature acquisition.

Deep learning is a new field of machine learning, its motivation is to establish and simulate the human brain for analytical learning neural network, which imitates the mechanism of the human brain to interpret data, such as images, sounds and texts.

two。 Advantages and disadvantages of deep learning

Traditional machine learning feature extraction mainly depends on manual, for specific simple tasks, manual feature extraction will be simple and effective, but it can not be universal. The feature extraction of deep learning does not depend on manual work, but is automatically extracted by machine.

The main advantages of ☆ deep learning are as follows:

Advantage 1: strong learning ability

From the results, deep learning has a strong learning ability, the performance is very good.

Advantage 2: wide coverage and good adaptability

The neural network of deep learning has many layers and wide breadth, and can be mapped to any function in theory, so it can solve very complex problems.

Advantage 3: data-driven, high upper limit

Deep learning is highly dependent on data, and the larger the amount of data, the better its performance. It is particularly outstanding in image recognition, facial recognition, NLP and other fields.

Advantage 4: good portability

Due to the excellent performance of deep learning, many frameworks can be used, such as TensorFlow, Pytorch. These frameworks are compatible with many platforms.

☆ deep learning also has its drawbacks:

Disadvantage 1: large amount of calculation and poor portability

Deep learning requires a lot of data and arithmetic, so the cost is very high. And now many applications are not suitable for use on mobile devices. At present, many companies and teams are developing chips for portable devices.

Disadvantage 2: high hardware requirements

Deep learning requires high numeracy, and ordinary CPU has been unable to meet the requirements of deep learning.

Disadvantage 3: model design is complex

The model design of deep learning is very complex, which requires a lot of manpower and time to develop new algorithms and models. Most people can only use ready-made models.

Disadvantage 4: without "human nature", it is easy to have prejudice.

Because deep learning depends on data, and the explanation is not high. In the case of uneven training data, there will be gender discrimination, racial discrimination and other problems.

three。 Three typical deep learning algorithms

Convolutional neural network (CNN), cyclic neural network (RNN) and generated countermeasure network (GAN) are three typical deep learning algorithms.

Convolution neural network is a kind of feedforward neural network with depth structure including convolution computation. It is one of the representative algorithms of deep learning.

CNN has great advantages in image processing. At present, it is widely used in image classification and retrieval, target location detection, target segmentation, face recognition, bone recognition and other fields.

Cyclic neural network is a kind of recurrent neural network which takes sequence data as input, recurses in the evolution direction of sequence and all nodes (cyclic units) are connected by chain.

In the field of deep learning, RNN is an algorithm that can effectively deal with sequential data. It is widely used in the fields of text generation, speech recognition, machine translation, image description, video tagging and so on.

Generating adversarial network is a deep learning model, and it is a very popular unsupervised learning algorithm in the past two years.

GAN can generate very realistic photos, images and even videos. It has a wide range of applications in many fields, such as generating image data sets, generating face photos, image-to-image conversion, text-to-image conversion, image editing, image restoration and many other fields.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.