In this article I want to give a quick presentation of the D2RL paper, applying deep dense architectures of neural networks for Deep Reinforcement Learning. The effect of large and dense network architectures has been long explored in Computer Vision and Deep Learning. The improved performance and other benefits of such dense models compared to shallow ones are widely established. Thereby, in Deep Reinforcement Learning, neural network architectures haven't gotten that much attention yet. Commonly used networks like policy or Q-function are usually only two layers deep.

Yann LeCun's deep learning course -- Deep Learning DS-GA 1008 -- at NYU Centre for Data Science has been made free and accessible online for all. The course will be led by Yann LeCun himself, along with Alfredo Canziani, an assistant professor of computer science at NYU, in Spring 2020. This deep learning course will focus on the latest techniques in deep learning and representation learning. It will also focus on an in-depth understanding of supervised and unsupervised deep learning, embedding methods, metric learning, and convolutional and recurrent nets. The course will further talk about the applications to computer vision, natural language understanding, and speech recognition.

Media manipulation through images and videos has been around for decades. For example, in WWII Mousollini released a propaganda image of himself on a horse with his horse handler edited out. The goal was to make himself seem more impressive and powerful [1]. These types of tricks can have significant impacts given the scale of people that see images like these, especially in the internet era. DARPA has an entire program constructed just to develop methods for detecting manipulated media through their media forensics (MEDIFOR) [2].

Learning rate is a hyperparameter with a small positive value (often range between 0.0 to 1.0) which controls how quickly the model adapts to the problem, in other words learning rates decides how far the weights should be in the direction of gradient to meet the global minimum. If the learning rate is too low (figure 1) training will progress very slowly. If the learning rate is set too high as it is shown in figure 3, training may not converge at the global minimum instead overshoots it and continue to make the loss of the model even worse. Getting the right learning rate at once is not possible (unless you are extremely experienced and lucky at the same time). As it is with all the hyperparameters it is a trial and error scenario.

Note on style - this initial blog post will be divided into three sections. In the first I will review what I understand to be the key points from the first chapter of the fastai book. In the second I will mention how, following the authors’ instructions, I setup a ‘workspace’ for DL. And finally I’ll discuss some open questions I have. Key points from Chapter 1 With this chapter Howard and Gugger provide a useful overview of the subject of Deep Learning, some extremely useful tips on how to setup a development environment for DL coding and analysis (more on that below) and provide a summary of their approach to teaching DL. The authors make great efforts to make the subject approachable, emphasising that neither advanced qualifications nor high level coding ability are necessary to implement Deep Learning techniques. Indeed, they say right from the beginning that they intend to give readers a sense of ‘the complete game’. I can say from experience of other courses or books in this area that this is a refreshingly different approach. They also provide a good overview of the history of the discipline - from McCulloch and Pitts’ notion of an artificial neuron to more contemporary concepts such as Parallel Distributed Processes (PDP). For me the most interesting topic is the difference between Machine Learning and more traditional forms of programming. From what I understand, traditional programming is based on the notion that inputs from the user will go through a function (defined by the programmer) and specific output(s) will be the result. This approach works well when, for example, we want to automate repetitive tasks. However it is not suitable for more complex or conceptual tasks, such as recognising the difference between a cat or dog, imitating a particular author’s writing style or making a good movie recommendation. The reason traditional approaches don’t work here is that a programmer would need to specify every single aspect relevant to the task. A far better approach then is one were the machine itself can ‘learn’ i.e. the programme (or model) has a process inherent to itself that enables it to output a result that is intelligible and accurate to humans. To make this clearer, I briefly touch on the solution that ultimately caught on, which was conceived by Arthur Samuel and called Machine Learning. ML essentially involves taking data, weighting it in some way (through labelling the data for instance) and training the programme (now referred to as a model) to recognise patterns within that data. This process will repeat, with the weights adjusting through each cycle, until the programmer considers the programme sufficiently accurate. Interestingly once the model is trained, it can be used in the manner of a traditional programme. That means novel data can be introduced, without weighting, and the model will then make predictions - again, for example, whether a picture shows a cat or dog. While this training process is based on repetition, training to frequently on the same data set will actually decrease accuracy. This is a situation known as over-fitting where the model makes predications to close to its training data. My summary here may sound very theoretical but Howard and Gugger present their account in quite a practical fashion with lots of coding and real life examples. Setting up a DL coding environment One surprising element of this course is the great advice that Howard and Gugger offer on how to set up your working environment for DL projects. In fact, this may have been the feature that ultimately persuaded me to work through the entire course. The best thing to do is check their site for the details link but just to give a brief summary of what they describe: Haward and Gugger have developed a framework called fastai that enables users to access DL techniques in PyTorch in a much more straightforward manner than is possible than through coding for PyTorch directly. (I’ve not personally used PyTorch but this is my understanding of what fastai does.) One consequence of this is that a GPU is required for fastai to function. I do not have a GPU in my rather cheap Lenovo laptop but not to worry as the authors provide a very useful, and thorough, guide on how to set up a cloud system to run the course exercises, which are written in standard Jupyter Notebooks (although Google Colab versions are also available). I would emphasise that this is in no way an intimidating or difficult process, in fact I’m almost stunned by how easy it is to set up a cloud computer. Personally I’m using a free service called Gradient which is offered by a company known as Paperspace. While there are some restrictions (such as the cloud system shutting down automatically after 6 hours) Paperspace have integrated fastai’s Jupyter Notebooks into their service, which means you can jump right in once you’ve set it up. The only complaint I have, and it’s very minor, is that for Paperspace do give you the option of running the course notebooks on systems without GPUs, which makes no sense since the notebooks won’t work without GPUs. Also a few times, when I’ve started the virtual machine, it seems to have automatically selected the CPU system. Anyway I certainly can’t complain, this is a great service and I think Paperspace should be given some credit for making DL this accessible for free to basically anyone. As a side note, another extremely useful discussion on setting up your coding environment can be found in Wes McKinney’s Python for Data Analysis. McKinney’s text focuses far more on the mechanics of data analysis, personally I see it more as a reference book than something I would read cover to cover. Nevertheless the opening chapter were he discusses the basics modules required for doing data analysis in Python is something I return to every time I setup a new PC. Open questions One point I’m not entirely clear on is how the theoretical notion of artificial neurons can produce intelligible results. Having done some other more mathematical focused courses on this subject I believe the reason that artificial neurons, in particular through layering, can do this is to with the fact they can be thought of as strings of matrix multiplications. This allows the system to compute linear algebra, which enable the computer to predict an answer. I’m not completely happy with my own explanation here. I do think at some point I will have to do a deep dive on the Maths but for now this is my understanding.

There is no question that the travel industry has been hit hard by the current pandemic. Places once packed to the gills with tourists now lie empty, and people are increasingly reluctant to travel given the risk of infection as well as quarantine requirements. However, all indications point to this travel freeze being temporary: the number of people traveling in the United States this August was higher than it has been compared to the past four months, and analysts predict that pent up demand for travel will provide a further boost to the hard-hit industry as restrictions lift and people's anxieties ease. This is a crucial moment for the industry as travel brands work to overcome the challenges imposed by COVID-19. Now more than ever, travel companies need the advanced capabilities of deep learning to unlock new opportunities and find innovative ways to reach new customers.

Machine Learning foners Second Edition has been written and designed for absolute beginners. This means plain-English explanations and no coding experience required. Where core algorithms are introduced, clear explanations and visual examples are added to make it easy and engaging to follow along at home. This major new edition features many topics not covered in the First Edition, including Cross Validation, Data Scrubbing and Ensemble Modeling.

Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL) are the buzzing technologies of this digital age. These three terms not only have different spellings but also refer to other things.

The news about artificial intelligence is mostly dominated by sensational stories such as the ominous threat of deepfakes, deep learning algorithms that create fake blogs, AI bots that create their own language, and generative adversarial networks that create realistic portraits of non-existent people. But the practical use of AI algorithms is much farther behind than the hype caused by the media. From peer-reviewed breakthrough research presented at mainstream AI conferences to PR-style videos created by large tech companies and well-funded research labs, only a trickle of the innovation we see in the field makes it into real business processes and applications. And the organizations that are putting AI to good use are those who understand the powers and limits of today's technology and master the challenges of integrating it into their processes and solutions. "AI does offer a lot of business value, but much of that value isn't terribly sexy or visible. Products and processes will be made somewhat better and easier to use. Decisions will be better informed. We'll continue -- and perhaps even accelerate a bit -- the amazing progress that we've seen over the last couple of decades in data and analytics. But as all of the early adopters have discovered, it's still difficult to create systems that think and communicate like humans -- even in narrow domains," academic and business author Thomas H. Davenport writes in his book The AI Advantage: How to Put the Artificial Intelligence Revolution to Work.

All MBA's will preach that Data-Driven Methods udemy discount Understand the value of data for businesses Learn to use Python, Pandas, Matplotlib & Seaborn, SkLearn, Keras, Tensorflow, NLTK, Prophet, PySpark, MLLib and more! Apply Data Science in Marketing to improve Conversion Rates, Predict Engagement and Customer Life Time Value Machine Learning from Linear Regressions (polynomial & multivariate), K-NNs, Logistic Regressions, SVMs, Decision Trees & Random Forests Unsupervised Machine Learning with K-Means, Mean-Shift, DBSCAN, EM with GMMs, PCA and t-SNE Build a Product Recommendation Tool using collaborative & item/content based Hypothesis Testing and A/B Testing - Understand t-tests and p values Natural Langauge Processing - Summarize Reviews, Sentiment Analysis on Airline Tweets & Spam Detection To use Google Colab's iPython notebooks for fast, relaible cloud based data science work Deploy your Machine Learning Models on the cloud using AWS This course takes on Machine Learning and Statistical theory and teaches you to use it in solving 20 real-world Business problems. Data Scientist is the buzz of the 21st century for good reason! The tech revolution is just starting and Data Science is at the forefront. As a result, "Data Scientist has become the top job in the US for the last 4 years running!" according to Harvard Business Review & Glassdoor.