🔰Industry Use Cases of Neural Networks🔰
What is Neural Network ?
📝Neural networks reflect the behavior of the human brain, allowing computer programs to recognize patterns and solve common problems in the fields of AI, machine learning, and deep learning.
Neural networks, also known as artificial neural networks (ANNs) or simulated neural networks (SNNs), are a subset of machine learning and are at the heart of deep learning algorithms. Their name and structure are inspired by the human brain, mimicking the way that biological neurons signal to one another.
Artificial neural networks (ANNs) are comprised of a node layers, containing an input layer, one or more hidden layers, and an output layer. Each node, or artificial neuron, connects to another and has an associated weight and threshold. If the output of any individual node is above the specified threshold value, that node is activated, sending data to the next layer of the network. Otherwise, no data is passed along to the next layer of the network.
Neural networks rely on training data to learn and improve their accuracy over time. However, once these learning algorithms are fine-tuned for accuracy, they are powerful tools in computer science and artificial intelligence, allowing us to classify and cluster data at a high velocity. Tasks in speech recognition or image recognition can take minutes versus hours when compared to the manual identification by human experts. One of the most well-known neural networks is Google’s search algorithm.
How do Artificial Neural Networks Work?
📝As we have seen Artificial Neural Networks are made up of a number of different layers.
Each layer houses artificial neurons called units. These artificial neurons allow the layers to process, categorize, and sort information. Alongside the layers are processing nodes. Each node has its own specific piece of knowledge. This knowledge includes the rules that the system was originally programmed with. It also includes any rules the system has learned for itself. This makeup allows the network to learn and react to both structured and unstructured information and data sets. Almost all artificial neural networks are fully connected throughout these layers. Each connection is weighted. The heavier the weight, or the higher the number, the greater the influence that the unit has on another unit. The first layer is the input layer. This takes on the information in various forms. This information then progresses through the hidden layers where it is analysed and processed. By processing data in this way, the network learns more and more about the information. Eventually, the data reaches the end of the network, the output layer. Here the network works out how to respond to the input data. This response is based on the information it has learned throughout the process. Here the processing nodes allow the information to be presented in a useful way.
What are the types of Neural Networks?
📝There are many types of neural networks available or that might be in the development stage. They can be classified depending on their: Structure, Data flow, Neurons used and their density, Layers and their depth activation filters etc.
We are going to discuss the following neural networks:
Perceptron
👉Perceptron model, proposed by Minsky-Papert is one of the simplest and oldest models of Neuron. It is the smallest unit of neural network that does certain computations to detect features or business intelligence in the input data. It accepts weighted inputs, and apply the activation function to obtain the output as the final result. Perceptron is also known as TLU(threshold logic unit). Perceptron is a supervised learning algorithm that classifies the data into two categories, thus it is a binary classifier.
Feed Forward Neural Networks
👉The simplest form of neural networks where input data travels in one direction only, passing through artificial neural nodes and exiting through output nodes. Where hidden layers may or may not be present, input and output layers are present there. Based on this, they can be further classified as a single-layered or multi-layered feed-forward neural network.
Number of layers depends on the complexity of the function. It has uni-directional forward propagation but no backward propagation. Weights are static here. An activation function is fed by inputs which are multiplied by weights. To do so, classifying activation function or step activation function is used. For example: The neuron is activated if it is above threshold (usually 0) and the neuron produces 1 as an output. The neuron is not activated if it is below threshold (usually 0) which is considered as -1. They are fairly simple to maintain and are equipped with to deal with data which contains a lot of noise.
Multilayer Perceptron
👉An entry point towards complex neural nets where input data travels through various layers of artificial neurons. Every single node is connected to all neurons in the next layer which makes it a fully connected neural network. Input and output layers are present having multiple hidden Layers i.e. at least three or more layers in total. It has a bi-directional propagation i.e. forward propagation and backward propagation.
Inputs are multiplied with weights and fed to the activation function and in backpropagation, they are modified to reduce the loss. In simple words, weights are machine learnt values from Neural Networks. They self-adjust depending on the difference between predicted outputs vs training inputs. Nonlinear activation functions are used followed by softmax as an output layer activation function.
Convolutional Neural Network
👉Convolution neural network contains a three-dimensional arrangement of neurons, instead of the standard two-dimensional array. The first layer is called a convolutional layer. Each neuron in the convolutional layer only processes the information from a small part of the visual field. Input features are taken in batch-wise like a filter. The network understands the images in parts and can compute these operations multiple times to complete the full image processing. Processing involves conversion of the image from RGB or HSI scale to grey-scale. Furthering the changes in the pixel value will help to detect the edges and images can be classified into different categories.
Propagation is uni-directional where CNN contains one or more convolutional layers followed by pooling and bidirectional where the output of convolution layer goes to a fully connected neural network for classifying the images as shown in the above diagram. Filters are used to extract certain parts of the image. In MLP the inputs are multiplied with weights and fed to the activation function. Convolution uses RELU and MLP uses nonlinear activation function followed by softmax. Convolution neural networks show very effective results in image and video recognition, semantic parsing and paraphrase detection.
Radial Basis Function Neural Networks
👉Radial Basis Function Network consists of an input vector followed by a layer of RBF neurons and an output layer with one node per category. Classification is performed by measuring the input’s similarity to data points from the training set where each neuron stores a prototype. This will be one of the examples from the training set.
When a new input vector [the n-dimensional vector that you are trying to classify] needs to be classified, each neuron calculates the Euclidean distance between the input and its prototype. For example, if we have two classes i.e. class A and Class B, then the new input to be classified is more close to class A prototypes than the class B prototypes. Hence, it could be tagged or classified as class A.
Each RBF neuron compares the input vector to its prototype and outputs a value ranging which is a measure of similarity from 0 to 1. As the input equals to the prototype, the output of that RBF neuron will be 1 and with the distance grows between the input and prototype the response falls off exponentially towards 0. The curve generated out of neuron’s response tends towards a typical bell curve. The output layer consists of a set of neurons [one per category].
Recurrent Neural Networks
👉Designed to save the output of a layer, Recurrent Neural Network is fed back to the input to help in predicting the outcome of the layer. The first layer is typically a feed forward neural network followed by recurrent neural network layer where some information it had in the previous time-step is remembered by a memory function. Forward propagation is implemented in this case. It stores information required for it’s future use. If the prediction is wrong, the learning rate is employed to make small changes. Hence, making it gradually increase towards making the right prediction during the backpropagation.
Sequence to sequence models
👉A sequence to sequence model consists of two Recurrent Neural Networks. Here, there exists an encoder that processes the input and a decoder that processes the output. The encoder and decoder work simultaneously — either using the same parameter or different ones. This model, on contrary to the actual RNN, is particularly applicable in those cases where the length of the input data is equal to the length of the output data. While they possess similar benefits and limitations of the RNN, these models are usually applied mainly in chatbots, machine translations, and question answering systems.
Modular Neural Network
👉A modular neural network has a number of different networks that function independently and perform sub-tasks. The different networks do not really interact with or signal each other during the computation process. They work independently towards achieving the output.
As a result, a large and complex computational process are done significantly faster by breaking it down into independent components. The computation speed increases because the networks are not interacting with or even connected to each other.
Why are neural networks important?
📝Neural networks are also ideally suited to help people solve complex problems in real-life situations. They can learn and model the relationships between inputs and outputs that are nonlinear and complex; make generalizations and inferences; reveal hidden relationships, patterns and predictions; and model highly volatile data (such as financial time series data) and variances needed to predict rare events (such as fraud detection). As a result, neural networks can improve decision processes in areas such as:
- Credit card and Medicare fraud detection.
- Optimization of logistics for transportation networks.
- Character and voice recognition, also known as natural language processing.
- Medical and disease diagnosis.
- Targeted marketing.
- Financial predictions for stock prices, currency, options, futures, bankruptcy and bond ratings.
- Robotic control systems.
- Electrical load and energy demand forecasting.
- Process and quality control.
- Chemical compound identification.
- Ecosystem evaluation.
- Computer vision to interpret raw photos and videos (for example, in medical imaging and robotics and facial recognition).
Advantages of Neural Networks
- A neural network can perform tasks that a linear program can not.
- When an element of the neural network fails, it can continue without any problem by their parallel nature.
- A neural network learns and does not need to be reprogrammed.
- It can be implemented in any application.
- It can be performed without any problem.
Limitations of Neural Networks
- The neural network needs the training to operate.
- The architecture of a neural network is different from the architecture of microprocessors, therefore, needs to be emulated.
- Requires high processing time for large neural networks.
Neural Networks in Healthcare
📝According to Wikipedia (the source of all truth) :
“Neural Networks are a computational approach which is based on a large collection of neural units loosely modeling the way the brain solves problems with large clusters of biological neurons connected by axons. Each neural unit is connected with many others…These systems are self-learning and trained rather than explicitly programmed…”
One way to think of it is this: Imagine that a doctor wants to make a prediction regarding a patient’s health — for instance, whether she or he is at risk of suffering from a certain disease. How would a doctor be able to ascertain that information? In most cases, it would involve using blood tests, taking tests of the patient’s vitals, and more to identify features that have proven to be good predictors of patient health. However, what if doctors only know a handful of risk-factors for a specific disease — or worse, they don’t know the risk factors at all? It would be impossible to make predictions.
ANNs help to provide the predictions in healthcare that doctors and surgeons simply couldn’t address alone. They work in moments wherein we can collect data, but we don’t understand which pieces of that data are vitally important yet. These abstractions can therefore capture complex relationships that might not be initially obvious — leading to better prediction for public health.
What are the Possibilities for Neural Networks in Healthcare?
📝ANNs have been used in healthcare for several decades. In fact, the book “Neural Networks in Healthcare” covers the various uses of this system prior to 2006. Before 2006, the main successes of ANNs were found in areas like speech processing and image processing. Today, as new technologies emerge, capable of changing the way that we approach neural networks in the first place — it’s worth noting that there may be numerous new options for changing the industry. Today, the possibilities for Neural Networks in Healthcare include:
- Diagnostic systems — ANNs can be used to detect heart and cancer problems, as well as various other diseases informed by big data.
- Biochemical analysis — ANNs are used to analyze urine and blood samples, as well as tracking glucose levels in diabetics, determining ion levels in fluids, and detecting various pathological conditions.
- Image analysis — ANNs are frequently used to analyze medical images from various areas of healthcare, including tumor detection, x-ray classifications, and MRIs.
- Drug development — Finally, ANNs are used in the development of drugs for various conditions — working by using large amounts of data to come to conclusions about treatment options.
Current Examples of Neural Networks
📝Neural networks can be seen in most places where AI has made steps within the healthcare industry. For instance, in the world of drug discovery, Data Collective and Khosla Ventures are currently backing the company “Atomwise“, which uses the power of machine learning and neural networks to help medical professionals discover safer and more effective medicines fast. The company recently published its first findings of Ebola treatment drugs last year, and the tools that Atomwise uses can tell the difference between toxic drug candidates and safer options.
Similarly, options are being found that could insert neural networks into the realm of diagnostic. For instance, in 2014, Butterfly Networks, which are transforming the diagnostic realm with deep learning, devices, and the cloud, raised $100M for their cause. This organization currently works at the heart of the medicine and engineering sectors by bringing together world-class skills in everything from electrical engineering, to mechanical engineering, and medicine. At the same time, iCarbonX are developing artificial intelligence platforms to facilitate research relating to the treatment of various diseases and preventative care. The company believe that soon they will be able to help enable the future of truly personalized medicine.
The Future of Healthcare
📝Perhaps the most significant problem with ANNs is that the learned features involved when it comes to assessing huge amounts of data can sometimes be difficult to interpret. This is potentially why ANNs are more commonly used during situations wherein we have a lot of data to ensure that the observed data doesn’t contain too many “flukes”. Think of it this way — if you toss a coin three times and receive “tails” every time, this doesn’t mean that a coin only has a “tails” side. It just means that you need further evaluation and more testing to get a proper reading of probability.
ANNs are going to need some tweaking if they’re going to become the change that the healthcare industry needs. However, alongside new AI developments, it seems that neural networks could have a very important part to play in the future of healthcare.
