DEEP_LEARNING_Lecture1 for btech students.pptx
- 2. Benefits or advantages of Deep Learning Following are the benefits or advantages of Deep Learning: Features are automatically deduced and optimally tuned for desired outcome. Features are not required to be extracted ahead of time. This avoids time consuming machine learning techniques. Robustness to natural variations in the data is automatically learned.
- 3. • The same neural network based approach can be applied to many different applications and data types. • Massive parallel computations can be performed using GPUs and are scalable for large volumes of data. Moreover it delivers better performance results when amount of data are huge. • The deep learning architecture is flexible to be adapted to new problems in the future.
- 4. Drawbacks or disadvantages of Deep Learning Following are the drawbacks or disadvantages of Deep Learning:: It requires very large amount of data in order to perform better than other techniques. It is extremely expensive to train due to complex data models. Moreover deep learning requires expensive GPUs and hundreds of machines. This increases cost to the users.
- 5. • There is no standard theory to guide you in selecting right deep learning tools as it requires knowledge of topology, training method and other parameters. As a result it is difficult to be adopted by less skilled people. • It is not easy to comprehend output based on mere learning and requires classifiers to do so. Convolutional neural network based algorithms perform such tasks.
- 6. Deep Learning The Wrong Way If you ask a deep learning practitioner how to get started with neural networks and deep learning, what do they say?
- 7. They say things like- • You must have a strong foundation in linear algebra. • You must have a deep knowledge of traditional neural network techniques. • You really must know about probability and statistics.
- 8. • You should really have a deep knowledge of machine learning. • You probably need to be a PhD in computer science. • You probably need 10 years of experience as a machine learning developer.
- 9. Why Deep Learning Learning Understanding the latest advancements in artificial intelligence can seem to two very popular concepts Machine Learning and Deep Learning. But lately, Deep Learning is gaining much popularity due to it’s supremacy in terms of accuracy when trained with huge amount of data.
- 11. Requiring high-performance GPUs, deep learning models utilize large amounts of labeled data. That driverless Tesla car that you are sitting behind needed millions of images and thousands of hours of video before gaining the ability to drive you
- 12. What is AI? Artificial intelligence is imparting a cognitive ability to a machine. The benchmark for AI is the human intelligence regarding reasoning, speech, and vision. This benchmark is far off in the future.
- 13. 1-Narrow AI: A artificial intelligence is said to be narrow when the machine can perform a specific task better than a human. The current research of AI is here now 2-General AI: An artificial intelligence reaches the general state when it can perform any intellectual task with the same accuracy level as a human would 3-Active AI: An AI is active when it can beat humans in many tasks Early AI systems used pattern AI has three different levels:
- 14. Deep Learning requires high-end machines contrary to traditional Machine Learning algorithms. GPU has become a integral part now to execute any Deep Learning algorithm. Machine Learning vs Deep Learning
- 15. 1. In traditional Machine learning techniques, most of the applied features need to be identified by an domain expert in order to reduce the complexity of the data and make patterns more visible to learning algorithms to work. 2. The biggest advantage Deep Learning algorithms as discussed before are that they try to learn high- level features from data in an incremental manner. This eliminates the need of domain expertise and hard core feature extraction. Machine Learning vs Deep Learning
- 17. 3. Another major difference between Deep Learning and Machine Learning technique is the problem solving approach. 4. Deep Learning techniques tend to solve the problem end to end, where as Machine learning techniques need the problem statements to break down to different parts to be solved first and then their results to be combine at final stage.
- 18. When to use Deep Learning 1. Deep Learning out perform other techniques if the data size is large. But with small data size, traditional Machine Learning algorithms are preferable. 2. Deep Learning techniques need to have high end infrastructure to train in reasonable time.
- 19. 3. When there is lack of domain understanding for feature introspection, Deep Learning techniques outshines others as you have to worry less about feature engineering. 4. Deep Learning really shines when it comes to complex problems such as image classification, natural language processing, and speech
- 20. In the table below, we summarize the difference between machine learning and deep learning.
- 21. Difference between Machine Learning and Deep Learning
- 22. What is Deep Learning Deep learning is a type of machine learning that mimics the neuron of the neural networks present in the human brain. Computer Vision Deep learning models are trained on a set of images, to solve a task. These deep learning models are mainly used in the field of Computer Vision which allows a computer to see and visualize like a human would.
- 23. Deep learning models can be visualized as a set of points each of which makes a decision based on the inputs to the node. This sort of network is similar to the biological nervous system, with each node acting as a neuron within a larger network.
- 24. Elaborately, a deep learning technique learn categories incrementally through it’s hidden layer architecture, defining low-level categories like letters first then little higher level categories like words and then higher level categories like sentences. In the example of image recognition it means identifying light/dark areas before categorizing lines and then shapes to allow face recognition.
- 25. Each neuron or node in the network represents one aspect of the whole and together they provide a full representation of the image. Each node or hidden layer is given a weight that represents the strength of its relationship with the output and as the model develops the weights are adjusted.
- 27. 1. It can also prescribe medicine used in medication. 2. Computer vision and pattern recognition 3. Robotics — Deep Learning systems have been taught to play games and even made to taught WIN games. 4. Facial recognition What Deep Learning can do?
- 28. 5. Precision agriculture 6. Fashion technology 7. Autonomouse vehicles 8. Drone and 3D mapping 9. Post estimation in Sports analytics & Retail markets
- 29. 10. Security & Surveillance 11. Chatbots for sales & marketing 12. Audio / Voice recognition 13. Restoring sound in video
- 30. Deep learning algorithms are constructed with connected layers.
- 31. The first layer is called the Input Layer The last layer is called the Output Layer All layers in between are called Hidden Layers. The word deep means the network join neurons in more than two layers.
- 32. Each Hidden layer is composed of neurons. The neurons are connected to each other. The neuron will process and then propagate the input signal it receives the layer above it. The strength of the signal given the neuron in the next layer depends on the weight, bias and activation function.
- 33. The network consumes large amounts of input data and operates them through multiple layers; the network can learn increasingly complex features of the data at each layer.
- 34. Deep learning Process. A deep neural network provides state-of-the-art accuracy in many tasks, from object detection to speech recognition. They can learn automatically, without predefined knowledge explicitly coded by the programmers.
- 36. A neural network works quite the same. Each layer represents a deeper level of knowledge, i.e., the hierarchy of knowledge. A neural network with four layers will learn more complex feature than with that with two layers.
- 37. The learning occurs in two phases. The first phase consists of applying a nonlinear transformation of the input and create a statistical model as output. The second phase aims at improving the model with a mathematical method known as derivative.
- 38. The neural network repeats these two phases hundreds to thousands of time until it has reached a tolerable level of accuracy. The repeat of this two-phase is called an iteration. Continue..
- 39. 1-Shallow neural network: The Shallow neural network has only one hidden layer between the input and output. Classification of Neural Networks.
- 40. 2-Deep neural network: Deep neural networks have more than one layer. For instance, Google LeNet model for image recognition counts 22 layers. Nowadays, deep learning is used in many ways like a driverless car, mobile phone, Google Search Engine, Fraud detection, TV, and so on.
- 41. Types of Deep Learning Networks-
- 42. Convolutional neural networks (CNN) CNN is a multi-layered neural network with a unique architecture designed to extract increasingly complex features of the data at each layer to determine the output. CNN's are well suited for perceptual tasks.
- 43. CNN is mostly used when there is an unstructured data set (e.g., images) and the practitioners need to extract information from it
- 44. The CNN receives an image of let's say a cat, this image, in computer term, is a collection of the pixel. Generally, one layer for the greyscale pictureand three layers for a color picture. During the feature learning (i.e., hidden layers), the network will identify unique features, for instance, the tail of the cat, the ear, etc. For instance, if the task is to predict an image caption:
- 45. When the network thoroughly learned how to recognize a picture, it can provide a probability for each image it knows. The label with the highest probability will become the prediction of the network.
- 46. RNN is a multi-layered neural network that can store information in context nodes, allowing it to learn data sequences and output a number or another sequence. In simple words it an Artificial neural networks whose connections between neurons include loops. RNNs are well suited for processing sequences of inputs. Recurrent neural networks (RNNs)
- 48. Common uses of RNN- Help securities traders to generate analytic reports. Detect abnormalities in the contract of financial statement. Detect fraudulent credit-card transaction. Provide a caption for images.
- 49. Common uses of RNN- Power chatbots. The standard uses of RNN occur when the practitioners are working with time-series data or sequences (e.g., audio recordings or text). Continue.
- 50. Reinforcement learning is a subfield of machine learning in which systems are trained by receiving virtual "rewards" or "punishments," essentially learning by trial and error. Google's Deep Mind has used reinforcement learning to beat a human champion in the Go games. Reinforcement learning is also used in video games to improve the gaming Reinforcement Learning