Deep Learning is a discipline that is already changing how we approach and apply Artificial Intelligence globally. Learn about it now and ensure your future success.
My courses are hands-on introductions to training and understanding Deep Neural Networks and their different fields of application. As you will learn, Deep Learning is a subfield of Machine Learning and applicable to all types of data. This contains but is not limited to images, texts, sounds, and statistical data.
We live in the age of Artificial Intelligence Democratization. Today, everyone can do Deep Learning. Everyone has access to data, algorithms, tools, frameworks, and machinery. All you need is a knowledge kickstart. And my classes are the perfect way to do that!
About the courses
I provide highly interactive classes in which your team will learn to do Deep Learning with Python, TensorFlow, and Keras. I will teach all you need to know in fruitful discussions. And your team members will be programming on their own computers under my guidance. This way we make sure that we engage both brain and muscle memory.
My classes were very successful in the past. They enabled a lot of talented individuals to do Deep Learning. What about you, your team and your company? Do you want to learn and apply Deep Learning?
If you are part of a company with an office in Europe, especially in Germany, you can invite me to train your team. ➥ Contact me if you are interested and for a non-binding offer.
Languages: English, German.
Available Courses.
I offer multiple courses that each focus on a different direction of Deep Learning. Is your area of interest not covered? Please drop me a line and I will see what I can do.
Training 1: Introduction to Deep Learning
This training is the entry-point to Deep Learning. I will introduce you to the field and provide you with working knowledge that allows you to apply Deep Learning to your use-cases.
Two days of hands-on training containing:
- Learn the Deep Learning basics. What is the difference between Artificial Intelligence, Machine Learning, and Deep Learning? Are they all the same?
- Explore Python for Deep Learning. We will have a look at Jupyter notebooks, relevant modules, and how to go production ready with your Neural networks.
- Consider Deep Learning workstations. What kinds of hardware and software guarantee success?
- Investigate why it is time for Deep Learning. How to come to train your first Neural Network in about one hour of work?
- Apply Deep Learning for classifications and regressions. Learn how to classify data such as texts, and images. And learn how to extrapolate new data from experiences.
- Learn about the basic Neural Network Building Blocks. What are models, layers, losses, metrics, activation functions and optimizers?
- Establish a reusable template of a Neural Network training pipeline. Start with data of any sort and end with an evaluated Neural Network.
- Learn and apply Deep Learning best practices. Grow a good understanding about hyper-parameter tuning.
➥ Contact me if you are interested and for a non-binding offer.
Training 2: Deep Learning for Image Processing
Today Deep Learning is dominating all Image Processing use-cases. On top of that, you will find many low-hanging fruits in that area. Prototyping is very easy.
Two days of hands-on training containing:
- Understand why the field of Image Processing is now dominated by Deep Neural Networks.
- Investigate the ImageNet-moment of AI history. We will find out why out of the sudden Deep Neural Networks became the singular game-changer in feature extraction and image classification.
- Learn about Neural Network layers that are specialised to Images Processing. Apply CNNs to learn a visual hierarchy.
- Implement image-data-generators. We will establish data-processing pipelines that bridge the grap between your raw data and Neural Network training.
- Explore Transfer Learning. What is this powerful technique that allows you to use a pre-trained Deep Neural Network and fit it to your use-cases?
- Examine the wide range of use-cases in the image-processing domain.
➥ Contact me if you are interested and for a non-binding offer.
Training 3: Deep Learning for Natural Language Processing
Natural Language Processing is the second field in which Deep Learning is dominating. We regularly hear about more and more approaches with higher and higher accuracies in processing language data.
Two days of hands-on training containing:
- Learn about the main Deep Learning Building blocks for Natural Language processing.
- Learn about the essential Neural Network layers that are most useful for Natural Language Processing.
- Examine different encodings and embeddings for language data.
- Do math-magic with words and sentences. We map texts to numbers that carry the semantics and make good use of this.
- Learn about special Neural Network layers that are excellent when it comes to sequential data such as texts.
- Establish a data pipeline for your texts. Starting with raw texts, analysing it and arriving at preprocessed data that is ready for Deep Neural Network Training.
- Research different means for transfer learning in Natural Language Processing. How to stand on the shoulders of text-processing giants and use their groundbreaking results.
➥ Contact me if you are interested and for a non-binding offer.
Training 4: Deep Learning for Time Series Analysis
Time Series Analysis is all about learning from past data and predicting the future. Deep Learning is perfect for finding and exploiting pattern in your data that you might not be aware of.
Two days of hands-on training containing:
- Have a look at the Deep Learning building blocks that are most useful in Time Series Analysis.
- Learn how Time Series Analysis can help you saving and making money if you have data to train on.
- Learn about specialised Neural Network layers that are perfect for data that is ordered over time.
- Examine how Deep Learning can be combined with Big Data.
➥ Contact me if you are interested and for a non-binding offer.
Training 5: Representation Learning and Unsupervised Learning with Deep Neural Networks
Although Deep Learning is known to be very successful in Supervised Learning it is also perfectly applicable to Unsupervised Learning. You can do a lot of great things with unlabelled data and Deep Neural Networks.
Two days of hands-on training containing:
- Get acquainted with the topic and build a solid understanding of this very relevant field.
- Experiment with the main Deep Learning building blocks for Representation Learning and Unsupervised Learning.
- Explore the notion of latent spaces and embeddings. Here we will have a look how you can map almost any data to lists of numbers. And we will also find how that these numbers can be used for computing distances, similarities and differences.
- Learn about Generative Adversarial Networks. These allow you to create new data from your data-sets.
- Understand and apply Autoencoders and Variational Autoencoders. How to apply Deep Learning to clustering? How would you build a recommender system using Deep Learning?
- Investigate the powerful technology called Triplet-Loss. It allows you to solve identification tasks with a very small amount of data and a high accuracy.
➥ Contact me if you are interested and for a non-binding offer.
Training 6: Deep Reinforcement Learning
Deep Reinforcement Learning is the next big thing in Artificial Intelligence. It is all about enabling a Deep-Learning-based intelligent agent to learn to solve a given problem. All by allowing it to find the best strategies on its own.
Two days of hands-on training containing:
- Understand the theory behind Deep Reinforcement Learning. What are the building blocks and how do they work and interact?
- Learn how a neural Network beat multiple world champions in the game of Go just recently.
- Understand that reward-modelling is the most crucial aspect of Deep Reinforcement Learning.
- Examine the big differences between Deep Learning and Deep Reinforcement learning. Expand you understanding towards the notion that goal-driven training is the next great leap after data-driven training.
- Get to know different kinds of Deep Reinforcement Learning agents. What is available and what is the current state of the art in this quickly growing field?
- Experiment with OpenAI Gym and train your own Deep Reinforcement Learning agents.
- Investigate the mass of use-cases that are available. Deep Reinforcement Learning is definitely not limited to games. Amongst other things, you could even apply it to cooling controllers in data centers.
➥ Contact me if you are interested and for a non-binding offer.
