دانلود کتاب یادگیری عمیق و کاربردهای آن با استفاده از پایتون

Research into deep learning has come a long way across multiple domains, such as healthcare, marketing, banking, manufacturing, education, and so on. Notable applications within these domains are trending, like visual recognition, fraud detection, virtual assistance, NLP, etc. Deep learning models are used to implement these applications. Those models include Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and others. To deploy these application-based deep learning models, Python programing is ideal, with its open source software libraries like keras, tensorflow, and soon. This book thoroughly explains deep learning models and how to use Python programming to implement them in applications such as NLP, face detection, face recognition, face analysis, and virtual assistance (chatbot, machine translation, etc.). This book provides hands-on guidance to using Python for implementing deep learning application models. It also identifies future research directions for deep learning. Chapter 1 deals with the history of deep learning. The origin tracks back to 1943, when Walter Pitts and Warren McCulloch computed a model (computer model) that supported the human brain (the neural networks). To mimic the thought processes of humans, Pitts and McCulloch used a collection of algorithms and arithmetic concepts, called threshold logic. Since then, deep learning has continuously evolved. TensorFlow and Keras play a major role in the implementation of deep learning models. Therefore, Chapter 2 explains TensorFlow fundamentals, based on a deep learning framework. TensorFlow plays a major role in pattern recognition, specifically in regards to language, images, sound, and time-series data. Classification, prediction, clustering, and feature extraction occurs, too, with the help of deep learning. Chapter 3 explains how a Python library called Keras has been used for deep learning. The chapter outlines the objective and focus of Keras to create neural networks layers and mathematical models. Chapter 4 continues the presentation of intelligent learning algorithms, explaining how multilayer perceptron is one of the supervised learning algorithms and is an example of artificial neural network with a feedback loop. Among other deep learning models, Chapter 5 delves into CNN algorithms, which act as an artificial neuron (neural network). This neural network is widely used to deal with image input for image processing, recognition, and classification. A Chapter 6 deals with RNN and LSTM, which are deep learning algorithms that can be used for sequencing numerical inputs to enable tasks, such as handwritten recognition without segmentation or speech recognition. In Chapter 7, the importance of artificial intelligence and its vital role in communicating with humans and machines, as shown in the form of text or voice. Programs that can converse naturally with humans are called chatbots, and this chapter explores have chatbots can be automated to perform user-performed tasks. Chapter 8 discusses different advanced models of deep learning algorithms that are used frequently. Upgrades or modifications are possible because of the flexible nature of neural network, which can lead to the design of an end-to-end model. Therefore, this advancement allows researchers to build simple to complex structures that align need with imagination. Some advanced deep learning algorithms include AlexNet, VGG, NiN, GoogLeNet, ResNet, DenseNet, GRU, LSTM, D-RNN, and Bi-RNN. These advanced deep learning algorithms are discussed in detail, along with code for implementation using Python’s Keras library on the TensorFlow platform. Chapter 9 includes a detailed discussion on new trends in deep learning, current and future challenges, and its prospects. The chapter is supported by a practical case study and working proofs. Some notable works highlighted in this chapter come from different domains, such as semantic intelligence, quantum AI, cyber security, the LAMSTAR system, epilepsy seizure onset prediction, etc.