va and xav
Task1:Summary:
Read the Case Study and answer the “Discussion Points” in a clear but concise way. Be sure to reference all sources cited and use APA formatting throughout.(attached casestudy-words:500)
Task2:please provide replies to below student posts– first 2 in 100 words.next 2 in 150
Ramesh- Discuss the advances in Neural Networks and how ANN, CNN work to classify image datasets more effectively.
Over several decades, since their invention, there have been numerous advancements in neural networks. The advancements being made are to ensure that the neural network can work as perfect as the human brain. Though the pointy of full autonomy is yet to be achieved, the progress so far can speak for itself (Almási, Woźniak, Cristea, Leblebici & Engbersen, 2016). Machines today with the implementation of advanced AI and machine learning, they are able to perform tasks that are otherwise considered to be a human prerogative. With the right knowledge base, intelligent machines can partially perform the task even in an uncertain environment, which is a great achievement (Almási et al., 2016).
CNN and ANN are both neural networks methodology used in the implementation process. When advancing neural networks, it means you have to advance the method used to implement the neural network. These two methods are critical in the selection of the features to use for raining as well as testing and implementation of the model (Shukla & Bhateja, 2018). Given that the two methods are from the same group of deep learning, the process of feature extraction, as well as classification, are performed simultaneously.
For ANN and CNN to learn, it compares the actual value with the output values. The speed of the learning process depends on weight variability, and in case of an error, the error is back propagated where the weights are varied accordingly to void the error. However, unlike CNN, all the neurons in ANN are interconnected (Shukla & Bhateja, 2018).
Ravi-A neural network is a series of algorithms that endeavors to recognize underlying relationships in sets of data through a process similar to how the human brain does. It tries as much to mimic how the human brain processes through the change in inputs amongst other factors and generating the best outcome without having to redesign the predetermined output criteria (Zeng & Wang, 2010). The recent advances in neural networks have helped humans in this age of computerization where almost everything is being done with the aid of electronic devices. With this neural networks machines are enabled and can now work without the supervision of their human masters as they will be programmed to work the same way the human would have supervised them to work. This is made possible through the use of artificial intelligence amongst other technological developments that have risen in the current age. Neural networks will not only aid in rocket science and other complex human operations but also day to day activities including in the entertainment industry, everyday interfaces, business intelligence amongst many other uses.
ANN and CNN are changing how we interact with the real world as they are the core of deep learning revolution powering powerful technologies such as facial recognition, self driving cars, unmanned space stations amongst may others. These networks are capable of learning non-linear functions and are capable of learning weights that map outputs to their respective inputs. They can also learn filters place automatically without having to mention them explicitly. These feature helps in extracting the the right and relevant features from the data input provided. They help in the identifying of objects correctly and determining their location of an object in the image, as well as their relations with other objects in the image. They also capture the spatial features from an image to increase the accuracy .
