AI Capstone Project with Deep Learning

Start Date: 02/16/2020

Course Type: Common Course

Course Link:

Explore 1600+ online courses from top universities. Join Coursera today to learn data science, programming, business strategy, and more.

About Course

In this capstone, learners will apply their deep learning knowledge and expertise to a real world challenge. They will use a library of their choice to develop and test a deep learning model. They will load and pre-process data for a real problem, build the model and validate it. Learners will then present a project report to demonstrate the validity of their model and their proficiency in the field of Deep Learning. Learning Outcomes: • determine what kind of deep learning method to use in which situation • know how to build a deep learning model to solve a real problem • master the process of creating a deep learning pipeline • apply knowledge of deep learning to improve models using real data • demonstrate ability to present and communicate outcomes of deep learning projects

Deep Learning Specialization on Coursera

Course Introduction

AI Capstone Project with Deep Learning In this Capstone you will design a real world AI system. You will use Deep Learning technology to design a complete AI system, from hardware development all the way to the field of AI policy. You will use a combination of lectures, hands-on labs and hands-off tutorials to get up to speed. You will also get to put all of this into practice by coding up the connected systems in C++ using NVIDIA MX150 GPUs. All of the features of this course are available for free. You do not need to pay for it! We have partnered with 3D-Bending to bring you hands-on exercises and videos. This is the third course in our 3D-Bending specialization. The goal of the specialization is to get you to design and program a complete 3D-animation system. This is where you will find the needed skills and knowledge to complete the capstone project. In the hands on labs you will see a complete humanoid robot system that you will need to interface with your smartphone to complete. The final design will include the complete system architecture, logic and communication, and will require the use of both hardware and software combined with a deep learning pipeline. The hands on labs will give you the opportunity to see everything that has to be done to make sure the design is ready to go and running again after the capstone. In the Deep Learning Pipeline you will use the latest and greatest deep learning algorithms to create your own AI system

Course Tag

Related Wiki Topic

Article Example
Deep learning Deep learning (also known as deep structured learning, hierarchical learning or deep machine learning) is a class
Deep learning Deep learning is often presented as a step towards realising strong AI and thus many organizations have become interested in its use for particular applications. In December 2013, Facebook hired Yann LeCun to head its new artificial intelligence (AI) lab that was to have operations in California, London, and New York. The AI lab will develop deep learning techniques to help Facebook do tasks such as automatically tagging uploaded pictures with the names of the people in them. Late in 2014, Facebook also hired Vladimir Vapnik, a main developer of the Vapnik–Chervonenkis theory of statistical learning, and co-inventor of the support vector machine method.
Deep learning A deep Q-network (DQN) is a type of deep learning model developed at Google DeepMind which combines a deep convolutional neural network with Q-learning, a form of reinforcement learning. Unlike earlier reinforcement learning agents, DQNs can learn directly from high-dimensional sensory inputs. Preliminary results were presented in 2014, with a paper published in February 2015 in Nature The application discussed in this paper is limited to Atari 2600 gaming, although it has implications for other applications. However, much before this work, there had been a number of reinforcement learning models that apply deep learning approaches (e.g.,).
Deep learning Compound hierarchical-deep models compose deep networks with non-parametric Bayesian models. Features can be learned using deep architectures such as DBNs, DBMs, deep auto encoders, convolutional variants, ssRBMs, deep coding networks, DBNs with sparse feature learning, recursive neural networks, conditional DBNs, de-noising auto encoders. This provides a better representation, allowing faster learning and more accurate classification with high-dimensional data. However, these architectures are poor at learning novel classes with few examples, because all network units are involved in representing the input (a "distributed representation") and must be adjusted together (high degree of freedom). Limiting the degree of freedom reduces the number of parameters to learn, facilitating learning of new classes from few examples. "Hierarchical Bayesian (HB)" models allow learning from few examples, for example for computer vision, statistics, and cognitive science.
Deep learning Deep learning exploits this idea of hierarchical explanatory factors where higher level, more abstract concepts are learned from the lower level ones. These architectures are often constructed with a greedy layer-by-layer method. Deep learning helps to disentangle these abstractions and pick out which features are useful for learning.
Deep learning A main criticism of deep learning concerns the lack of theory surrounding many of the methods. Learning in the most common deep architectures is implemented using gradient descent; while gradient descent has been understood for a while now, the theory surrounding other algorithms, such as contrastive divergence is less clear. (i.e., Does it converge? If so, how fast? What is it approximating?) Deep learning methods are often looked at as a black box, with most confirmations done empirically, rather than theoretically.
Deep learning These definitions have in common (1) multiple layers of nonlinear processing units and (2) the supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features. The composition of a layer of nonlinear processing units used in a deep learning algorithm depends on the problem to be solved. Layers that have been used in deep learning include hidden layers of an artificial neural network and sets of complicated propositional formulas. They may also include latent variables organized layer-wise in deep generative models such as the nodes in Deep Belief Networks and Deep Boltzmann Machines.
Deep learning Recommendation systems have used deep learning to extract meaningful deep features for latent factor model for content-based recommendation for music. Recently, a more general approach for learning user preferences from multiple domains using multiview deep learning has been introduced. The model uses a hybrid collaborative and content-based approach and enhances recommendations in multiple tasks.
Deep learning If there is a lot of learnable predictability in the incoming data sequence, then the highest level RNN can use supervised learning to easily classify even deep sequences with very long time intervals between important events. In 1993, such a system already solved a "Very Deep Learning" task that requires more than 1000 subsequent layers in an RNN unfolded in time.
Deep learning The first general, working learning algorithm for supervised deep feedforward multilayer perceptrons was published by Ivakhnenko and Lapa in 1965. A 1971 paper described a deep network with 8 layers trained by the Group method of data handling algorithm which is still popular in the current millennium. These ideas were implemented in a computer identification system "Alpha", which demonstrated the learning process. Other Deep Learning working architectures, specifically those built from artificial neural networks (ANN), date back to the Neocognitron introduced by Kunihiko Fukushima in 1980. The ANNs themselves date back even further. The challenge was how to train networks with multiple layers.
Deep learning Deep learning is part of a broader family of machine learning methods based on learning representations of data. An observation (e.g., an image) can be represented in many ways such as a vector of intensity values per pixel, or in a more abstract way as a set of edges, regions of particular shape, etc. Some representations are better than others at simplifying the learning task (e.g., face recognition or facial expression recognition). One of the promises of deep learning is replacing handcrafted features with efficient algorithms for unsupervised or semi-supervised feature learning and hierarchical feature extraction.
Deep learning Numerous researchers now use variants of a deep learning RNN called
Deep learning "Deep learning" has been characterized as a buzzword, or a rebranding of neural networks.
Deep learning Many deep learning algorithms are applied to unsupervised learning tasks. This is an important benefit because unlabeled data are usually more abundant than labeled data. Examples of deep structures that can be trained in an unsupervised manner are neural history compressors and deep belief networks.
Capstone course A capstone course, also known as capstone unit serves as the culminating and usually integrative experience of an educational program. A capstone course, unit, module or subject in the higher education context may also be referred to as a capstone experience, senior seminar (in the U.S.), or final year project or dissertation (more common in the U.K.).
Deep learning Since its resurgence, deep learning has become part of many state-of-the-art systems in various disciplines, particularly computer vision and automatic speech recognition (ASR). Results on commonly used evaluation sets such as TIMIT (ASR) and MNIST (image classification), as well as a range of large-vocabulary speech recognition tasks are constantly being improved with new applications of deep learning. Recently, it was shown that deep learning architectures in the form of convolutional neural networks have been nearly best performing; however, these are more widely used in computer vision than in ASR, and modern large scale speech recognition is typically based on CTC for LSTM.
Capstone Program In 2006, the FAA integrated the Alaskan Capstone project into the national Automatic Dependent Surveillance – Broadcast (ADS–B) program.
Capstone Development Capstone Development LLC is a privately held real estate development company based in Washington, D.C., in the United States. It was formed in 2009. As of January 2013, it owned six hotels along the East Coast and in the Deep South. The company has two subsidiaries. Capstone Management Services provides hotel management services, and Capstone Procurement provides food service and janitorial supplies for hotels.
Deep learning Deep learning algorithms transform their inputs through more layers than shallow learning algorithms. At each layer, the signal is transformed by a processing unit, like an artificial neuron, whose parameters are 'learned' through training. A chain of transformations from input to output is a "credit assignment path" (CAP). CAPs describe potentially causal connections between input and output and may vary in length – for a feedforward neural network, the depth of the CAPs (thus of the network) is the number of hidden layers plus one (as the output layer is also parameterized), but for recurrent neural networks, in which a signal may propagate through a layer more than once, the CAP is potentially unlimited in length. There is no universally agreed upon threshold of depth dividing shallow learning from deep learning, but most researchers in the field agree that deep learning has multiple nonlinear layers (CAP > 2) and Juergen Schmidhuber considers CAP > 10 to be very deep learning.
Capstone Publishers Capstone is a publisher of children’s books and digital products. Capstone focuses on the educational market. They also sell to the trade market and internationally. Capstone publishes nonfiction, fiction, picture books, interactive books, audio books, literacy programs, and digital media. Imprints and divisions include Capstone Press, Compass Point Books, Picture Window Books, Stone Arch Books, Red Brick Learning, Capstone Digital, Heinemann-Raintree and Switch Press. Capstone acquired the assets of Heinemann-Raintree library reference from Pearson Education in 2008. Heinemann-Raintree has offices in Chicago and Oxford, England. Capstone is based in Mankato, Minnesota, with additional offices in Minneapolis, Chicago, and Oxford. Capstone is part of Coughlan Companies, Inc. Coughlan Companies also includes Jordan Sands, a limestone quarry, and fabrication facility.