Neural Networks 강좌

Neural networks, also known as neural nets or artificial neural networks (ANN), are machine learning algorithms organized in networks that mimic the functioning of neurons in the human brain. Using this biological neuron model, these systems are capable of unsupervised learning from massive datasets.

This is an important enabler for artificial intelligence (AI) applications, which are used across a growing range of tasks including image recognition, natural language processing (NLP), and medical diagnosis. The related field of deep learning also relies on neural networks, typically using a convolutional neural network (CNN) architecture that connects multiple layers of neural networks in order to enable more sophisticated applications.

For example, using deep learning, a facial recognition system can be created without specifying features such as eye and hair color; instead, the program can simply be fed thousands of images of faces and it will learn what to look for to identify different individuals over time, in much the same way that humans learn. Regardless of the end-use application, neural networks are typically created in TensorFlow and/or with Python programming skills.‎

Neural networks are a fundamental concept to understand for jobs in artificial intelligence (AI) and deep learning. And, as the number of industries seeking to leverage these approaches continues to grow, so do career opportunities for professionals with expertise in neural networks. For instance, these skills could lead to jobs in healthcare creating tools to automate X-ray scans or assist in drug discovery, or a job in the automotive industry developing autonomous vehicles.

Professionals dedicating their careers to cutting-edge work in neural networks typically pursue a master’s degree or even a doctorate in computer science. This high-level expertise in neural networks and artificial intelligence are in high demand; according to the Bureau of Labor Statistics, computer research scientists earn a median annual salary of $122,840 per year, and these jobs are projected to grow much faster than average over the next decade.‎

Absolutely - in fact, Coursera is one of the best places to learn about neural networks, online or otherwise. You can take courses and Specializations spanning multiple courses in topics like neural networks, artificial intelligence, and deep learning from pioneers in the field - including deeplearning.ai and Stanford University. Coursera has also partnered with industry leaders such as IBM, Google Cloud, and Amazon Web Services to offer courses that can lead to professional certificates in applied AI and other areas. You can even learn about neural networks with hands-on Guided Projects, a way to learn on Coursera by completing step-by-step tutorials led by experienced instructors.‎

Before starting to learn neural networks, it's important to have experience creating and using algorithms since neural networks run on complicated algorithms. You should also have fundamental math skills at least, but you'll be at a better advantage if you have knowledge of linear algebra, calculus, statistics, and probability. Being proficient at problem-solving is also important before starting to learn neural networks. An understanding of how the human brain processes information is helpful since artificial neural networks are patterned after how the brain works. You'll also benefit from having experience using any programming language, in particular Java, R, Python, or C++. This includes experience using these languages' libraries, which you'll access to apply the algorithms used in neural networks.‎

People who are best suited for roles in neural networks are innovative, interested in technology, and have the ability to identify patterns in large amounts of data and draw conclusions from them. People who have a desire to make life and work easier for human beings through artificial technology are well suited for roles in neural networks too. Also, people who have good programming skills and data engineering skills like SQL, data analysis, ETL, and data visualization are likely well suited for roles in neural networks.‎

If you are interested in the field of artificial intelligence, learning about neural networks is right for you. If your current or future position involves data analysis, pattern recognition, optimization, forecasting, or decision-making, you might also benefit from learning neural networks. Neural networks are also used in image recognition software, speech synthesis, self-driving vehicles, navigation systems, industrial robots, and algorithms for protecting information systems, so if you're interested in these technologies, learning neural networks may be helpful to you.‎