Neural Networks Research and Applications
- Overview
The word "neural" was inspired by the word "neuron", and we all know what a neuron is. It helps humans process information and generate output through the brain. This neuron is interconnected with millions of other neurons. The same thing happens in artificial intelligence. Neural networks also interconnect artificial neurons called "nodes". We also call it an artificial neural network (DNN).
Neural networks are a key element of deep learning and artificial intelligence. What exactly is a neural network trying to do? Like any other model, it tries to make a good prediction. We have a set of inputs and a set of target values - we're trying to get predictions that match those target values as closely as possible.
All recent advances in AI in recent years have been attributed to deep learning. Without deep learning, we wouldn't have self-driving cars, chatbots, or personal assistants like Alexa and Siri. The Google Translate app will continue to be as primitive as it was 10 years ago (before Google switched to neural networks for this app), and Netflix or Youtube have no idea which movies or TV shows we like or dislike. Behind all these technologies are neural networks.
Deep learning is a subset of machine learning, and machine learning is a subset of artificial intelligence. Artificial intelligence is a general term referring to technologies that enable computers to mimic human behavior. Machine learning represents a set of algorithms trained on data that make this possible.
On the other hand, deep learning is just a type of machine learning, inspired by the structure of the human brain. Deep learning algorithms try to draw conclusions similar to humans by constantly analyzing data with a given logical structure. To achieve this, deep learning uses a multi-layered algorithmic structure called a neural network.
The image above shows a simple feed forward neural network that propagates information forwards.
- Neural Networks
The design of neural networks is based on the structure of the human brain. Just as we use the brain to recognize patterns and classify different types of information, neural networks can be taught to perform the same tasks on data.
The layers of a neural network can also be thought of as a kind of "coarse-to-fine filters", increasing the likelihood of detection and output of the correct result. The human brain works in a similar way. Whenever we receive new information, the brain tries to compare it with known objects. Deep neural networks also use the same concept.
Neural networks allow us to perform many tasks such as clustering, classification or regression. Using neural networks, we can group or rank unlabeled data based on the similarity between samples in the data. Or in the case of classification, we can train the network on a labeled dataset in order to classify the samples in that dataset into different classes. Artificial neural networks have the unique ability to enable deep learning models to solve tasks that machine learning models could never solve.
- Artificial Neural Networks (ANNs)
An artificial neural network (ANN), often referred to simply as a neural network, is a computational system inspired by the fuzziness of the biological neural networks that make up animal brains. ANNs are based on collections of connected units or nodes called artificial neurons (blue nodes in the diagram above), which loosely model neurons in biological brains. Each connection, like a synapse in a biological brain, can transmit signals to other neurons.
An artificial neuron (the blue node in the diagram above) receives the signal, processes it, and can send out signals to the neurons connected to it. The "signal" at the connection is a real number, and the output of each neuron is computed by some nonlinear function of the sum of its inputs. These connections are called edges. Neurons and edges typically have weights that are adjusted as learning progresses. The weight increases or decreases the signal strength at the connection.
A neuron may have a threshold so that it only sends a signal when the aggregated signal exceeds that threshold. Typically, neurons are aggregated into layers. Different layers can perform different transformations on their inputs. The signal propagates from the first layer (input layer) to the last layer (output layer), possibly after traversing the layers many times.
- Neural Networks and AI Research
Neural networks are an important area of AI research and are currently proving valuable for more natural user interfaces through speech recognition and natural language processing, allowing humans to interact with machines in the same way they interact with each other.
By design, neural networks mimic the biological functions of animal brains to interpret and respond to specific inputs, such as words and intonation. As the underlying technology continues to evolve, AI has the potential to enhance online learning, adaptive learning software, and simulations in ways that more intuitively respond to and engage with students.
While neural networks (also known as "perceptrons") have been around since the 1940s, they haven't become a staple of artificial intelligence until the last few decades. This is due to the advent of a technique called "backpropagation," which allows a network to adjust its hidden layers of neurons if the results don't match what the creators wanted -- such as those designed to recognize dogs network, it will misidentify, for example, a cat.
Another important advance has been the arrival of deep learning neural networks, where different layers of a multi-layered network extract different features until it can identify what it is looking for. The idea of deep learning is: use brain simulations with the hope of: (a) making learning algorithms better and easier to use. (b) Revolutionary advances in machine learning and artificial intelligence. This is our best chance to move towards true artificial intelligence
- Neural Networks and Deep Learning
Neural networks mirror the behavior of the human brain, enabling computer programs to recognize patterns and solve common problems in the fields of artificial intelligence, machine learning, and deep learning.
Deep Learning is a subfield of machine learning concerned with algorithms inspired by the structure and function of the brain called artificial neural networks. Deep Learning is Large Neural Networks.
The core of deep learning is that we now have fast enough computers and enough data to actually train large neural networks. Very large neural networks that we can now have, and huge amounts of data that we have access to, it is the time that deep learning is taking off.
As we construct larger neural networks and train them with more and more data, their performance continues to increase. This is generally different to other machine learning techniques that reach a plateau in performance. For most flavors of the old generations of learning algorithms, performance will plateau. Deep learning is the first class of algorithms that is scalable. Performance just keeps getting better as you feed them more data.