About the camp
Fundamentals of Deep Learning is an intermediate level camp focusing on the basics of neural networks, which are a popular and powerful way of solving complex machine learning problems. Workshops will deal with the basics of neural networks, such as their workings and architecture, combined with introductory hands-on projects in image recognition and text processing using the popular Python library Keras.
Our goal is to inspire and give you a good foundation to continue learning more about the field. The camp is perfect for you who have recently started your journey in Machine Learning and want to take your first step into the world of Deep Learning. We especially welcome people with different backgrounds as we believe that we can all learn from each other one step at a time.
When we are not coding, there will be the opportunity to do various online activities like yoga, joining in with a cook-along and listening to inspirational talks from the teachers and mentors. Despite being online, the camp will be a social occasion to learn together with others and get a network within the Machine Learning field.
For each day of the camp, we will be programming approximately between 9 am and 5 pm. Both before and after there will be other social or recreational activities to do.
Come join us to learn about both the mysteries and practicalities of Deep Learning!
- Basic Programming knowledge (preferably Python) including:
- Variables and data types
- Lists, tuples, dictionaries and for loops
- Conditional statements
- Good to know (if you do not meet the requirements, don't worry. Then we suggest you prepare by going through the tutorial links below before the camp)
- Pandas/Numpy or similar libraries in e.g. R (can you complete the exercises 1-5?)
- Matplotlib/Seaborn or similar libraries in e.g. R (can you draw a line chart? E.g. exercise 2)
- A little bit of familiarity with common Machine Learning problems and terminology:
- Preparing your data (identifying missing values, split into train and test set)
- The difference between regression and classification
- What it means for an algorithm to be supervised or unsupervised
- Some evaluation metrics (accuracy, precision, recall, MSE)
- Some basic knowledge of math/statistics (mean, standard, deviation)
There is no need to know very many algorithms or advanced evaluation methods! If you do, be aware that the course also welcomes participants who don't yet have that knowledge :)
Definitely not needed
- Masters in Machine Learning
- Professional Data Scientist
- Math genius
- Any previous knowledge of Deep Learning
Expected learning outcomes
- Introduction to the basic concepts (e.g. hidden layers, activation functions, forward-and backward propagation) in deep learning
- Introduction to popular tools and libraries such as Google Colab and Keras
- Hands-on experience with text processing using recurrent neural networks (RNN)
- Hands-on experience with image recognition using convolutional neural networks (CNN)
- Small introduction to image/video generation using generative adversarial networks (GAN)
- Real world application of deep learning
- Ethics and responsible AI