Home of RF and Wireless Vendors and Resources

One Stop For Your RF and Wireless Need

Advantages of Deep Learning | disadvantages of Deep Learning

This page covers advantages and disadvantages of Deep Learning. It mentions Deep Learning advantages or benefits and Deep Learning disadvantages or drawbacks.

What is Deep Learning?

• Machine Learning extracts the features of images such as corners and edges in order to create models of the various objects. It later uses these models to identify the objects. Machine learning does not require high performance processors and more data.
• Deep Learning is subtype of machine learning. Deep learning is a machine learning technique which learns features and tasks directly from data. The data can be images, text files or sound.

difference between machine learning and deep learning
Figure-1: Machine Learning Vs Deep Learning

The figure-1 depicts processes followed to identify the object in both machine learning and deep learning. Deep Learning does not require feature extraction manually and takes images directly as input. It requires high performance GPUs and lots of data. Feature extraction and classification are carried out by deep learning algorithms known as convolutional neural network (CNN). CNN takes care of feature extraction as well as classification based on multiple images. Performance of deep learning algorithms increases when amount of data increases. In contrast, performance of other learning algorithms decreases when amount of data increases. The same has been shown in the figure-2.

Deep Learning Performance
Figure-2: Deep Learning Performance

An artificial neural network contains hidden layers between input layers and output layers. Here artificial neurons take set of weighted inputs and produce an output using activation function or algorithm. Traditional neural network contains two or more hidden layers. Deep learning contains many such hidden layers (usually 150) in such neural network. Hence the name "deep" used for such networks. The same has been shown in the figure-3 below.

Number of Hidden layers in deep learning
Figure-3: Number of Hidden Layer

Following are some of the applications of deep learning which have pioneered its development.
• Object Detection or classification in photographs
• Automatic driving cars
• Automatic Game Playing
• Automatic Machine Translation
• Colorization of Black & White Images
• Automatic Handwriting generation
• Image Caption Generation
• Character Text Generation
• Adding sounds to silent movies
• Toxicity detection for different chemical structures
• Mitosis detection from large images
• Hallucination or Sequence generation
• Automated Essay Scoring tool for grading essays of students

Benefits or advantages of Deep Learning

Following are the benefits or advantages of Deep Learning:
➨Features are automatically deduced and optimally tuned for desired outcome. Features are not required to be extracted ahead of time. This avoids time consuming machine learning techniques.
➨Robustness to natural variations in the data is automatically learned.
➨The same neural network based approach can be applied to many different applications and data types.
➨Massive parallel computations can be performed using GPUs and are scalable for large volumes of data. Moreover it delivers better performance results when amount of data are huge.
➨The deep learning architecture is flexible to be adapted to new problems in the future.

Drawbacks or disadvantages of Deep Learning

Following are the drawbacks or disadvantages of Deep Learning:
➨It requires very large amount of data in order to perform better than other techniques.
➨It is extremely expensive to train due to complex data models. Moreover deep learning requires expensive GPUs and hundreds of machines. This increases cost to the users.
➨There is no standard theory to guide you in selecting right deep learning tools as it requires knowledge of topology, training method and other parameters. As a result it is difficult to be adopted by less skilled people.
➨It is not easy to comprehend output based on mere learning and requires classifiers to do so. Convolutional neural network based algorithms perform such tasks.

Data Mining Related Links

data mining tutorial    What is big data    What is Hadoop    advantages disadvantages of data mining    Data Mining Glossary    Data mining tools and techniques    IoT tutorial    Cloud Storage tutorial

Data Analytics Tutorial RELATED LINKS

What is data analytics    What is Data Cleansing    What is Data Deduping    What is Data Profiling    Advantages and Disadvantages of data analytics    What is big data    What is Hadoop    Data Mining Glossary    Data mining tools and techniques    What is Cloud Storage    data mining tutorial   

Advantages and Disadvantages

Refer advantages and disadvantages of following terms:
Data Fusion || Data Analytics || Data Mining || Machine Learning

What is Difference between

difference between OFDM and OFDMA
Difference between SC-FDMA and OFDM
Difference between SISO and MIMO
Difference between TDD and FDD

RF and Wireless Terminologies

Share this page

Translate this page