Introduction
Deep learning is a specialized form of machine learning that emphasizes training the computer about the basic instincts of human beings. In deep learning, a computer algorithm learns to perform classification tasks directly on complex data in the form of images, text, or sound. Deep learning is a key technology behind driverless cars, it is the key to voice control in consumer devices like phones, tablets, TVs, and hands-free speakers. These algorithms can achieve state-of-the-art (SOTA) accuracy, and in some cases, even outperform humans. Deep learning networks have the advantage of continuously improving as the size of your data grows. 
A successful deep learning application needs a lot of data (thousands of images) to train the model, as well as GPUs (graphics processing units) to analyze the data quickly. Consider whether you have a high-performance GPU and a lot of labelled data when deciding between machine learning and deep learning. If you don't have one of those qualities, machine learning may be a better option than deep learning. Deep learning is more complicated than traditional machine learning, so you'll need at least a few thousand photos to achieve solid results. The model will take less time to analyze all those images if it has a high-performance GPU.
Top 10 Deep Learning Algorithms in current Machine Learning world includes:
Multilayer Perceptron’s (MLPs)
Radial Basis Function Networks (RBFNs)
Convolutional Neural Networks (CNN)
Recurrent Neural Networks (RNNs)
Long Short-Term Memory Networks (LSTMs)
Restricted Boltzmann Machines (RBMs)
Self Organizing Maps (SOMs)
Generative Adversarial Networks (GANs)
Autoencoders
Deep Belief Network
Forecasting COVID-19 new cases using Deep Learning methods The global spread of the COVID-19 pandemic has caused massive economic losses, human life losses, and disruption of normal public life. Thus, one of the most important elements in preventing the spread of the pandemic in heavily affected countries such as India, Brazil, Russia, and others is understanding the spread and accurately forecasting the trends. Reliability in forecasting COVID-19 spread trends can help predict pandemic outbreaks and increase government preparedness to combat the pandemic.
Machine Learning models have been widely used in forecasting, and they can be particularly useful in pandemic planning. These models have been used to successfully understand various aspects of the pandemic, including developing machine learning models that can design antibodies, using medical image datasets, particularly chest X-rays, modeling and understanding mutations, detecting whether a patient is infected with SARS-CoV-2, and forecasting pandemic trends.
Three different deep learning models used: Convolutional neural network (CNN) Long short-term memory (LSTM) Convolutional neural network-Long short-term memory (CNN-LSTM)
Data Pre-processing: In Machine Learning, data preprocessing refers to the process of cleaning and organizing raw data to make it suitable for building and training Machine Learning models.
Convolutional neural network (CNN): Given a prediction task, these models can extract auto-mated features from the data. Previous research has validated the convolutional neural network's performance in analyzing time-series data due to its strong ability to extract features from data such as stock price forecasts, air quality forecasts, and energy load forecasting.
Long short-term memory (LSTM): LSTM networks are a type of recurrent neural network that can learn order dependence in sequence prediction problems. This is a necessary characteristic in complex problem domains such as machine translation, speech recognition, and others.
Convolutional neural network-Long short-term memory (CNN-LSTM): CNN layers for feature extraction on input data are combined with LSTMs to support sequence prediction in the CNN-LSTM architecture. CNN-LSTMs were created to solve visual time series prediction problems and to generate textual descriptions from image sequences.
 |
| forecasting covid 19 architecture |
 |
| CNN Diagram |
Architecture of a traditional CNN: Convolutional neural networks, also known as CNNs, are a specific type of neural networks that are generally composed of the following layers:
Machine learning means computers learning from data using algorithms to perform a task without being explicitly programmed.
Deep learning uses a complex structure of algorithms modeled on the human brain. This enables the processing of unstructured data such as documents, images, and text.
Deep learning allows computers to understand unstructured data and find meaningful links from enormous amounts of information/data. When it comes to complicated issues like image classification, natural language processing, and speech recognition, as well as big data sets, Deep Learning shines.
Reference
[1] Sarker, I.H. Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions. SN COMPUT. SCI. 2, 420 (2021)
[2] Lu Xu,Rishikesh Magar,Amir Barati Farimani : Forecasting COVID-19 new cases using deep learning methods, Elsevier under Computers in Biology and Medicine
Post a Comment