In this document we link some of the material that we consider relevant to become knowlegable in the field of Artificial Intelligence. We suggest you do the homeworks and implement the ideas from the papers, as they would make sure you understand the ideas. A few notes:

1. We do not consider ourselfs AI experts, so we are open to suggestions (please use PR).
2. We have not necessarily fully studied all this material, some of it is recommended by the community.
3. A lot of the content may seem a bit redundant, we hope you are wise enough to realize what you can ignore.

Conventions

The following tags are used to mark content at different levels:

• Type, related to the particular desired for study some conent:
• Level, the mastery of the subjects you will have after fully studied the content:
• Format, how the content is presented:

The badges may apply to a particular content, subsection or section of this document.

It is good to have this section here for reference, but we suggest you start with the core material and come back to this section if you feel lost in some ideas or tasks, specially if you have studied the prerequisites before.

Math

1. Linear Algebra:

• https://www.edx.org/course/linear-algebra-foundations-to-frontiers-0
• https://www.khanacademy.org/math/linear-algebra
• https://www.youtube.com/playlist?list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab

2. Differential Calculus:

• https://www.edx.org/course/calculus-1a-differentiation
• https://www.khanacademy.org/math/differential-calculus y https://www.khanacademy.org/math/multivariable-calculus
• https://www.youtube.com/playlist?list=PLZHQObOWTQDMsr9K-rj53DwVRMYO3t5Yr

3. Statistics and probability:

• https://www.amazon.com/Introduction-Mathematical-Statistics-Its-Applications/dp/0321693949
• https://www.khanacademy.org/math/statistics-probability

Programming

1. Algorithms and data structures:

• https://www.programiz.com/dsa#
• https://www.khanacademy.org/computing/computer-science/algorithms

2. Python:

• https://docs.python.org/3/tutorial/
• https://www.tutorialspoint.com/python/
• https://www.amazon.com/Fluent-Python-Concise-Effective-Programming/dp/1491946008

3. Numpy

• https://realpython.com/numpy-array-programming/
• http://cs231n.github.io/python-numpy-tutorial/
• https://docs.scipy.org/doc/numpy/user/quickstart.html
• https://www.tutorialspoint.com/numpy

Although it is true that AI is much more than Machine Learning and (therefore) Deep Learning, Deep Learning is a great deal of AI this days.

1. Artificial Intelligence (Columbia University)
2. Machine Learning:

• Machine Learning (Stanford, Andrew Ng)
• Machine Learning (Columbia University)
• Intro to Machine Learning (Udacity)
• Machine Learning (Oxford University)
• Hands-Machine-Learning-Scikit-Learn-TensorFlow
• Machine Learning Yearning(very good resource to structure machine learning projects).

3. Deep Learning:

• Deep Learning Specialization (the lectures can be seen for free on YouTube, in the official DeepLearning Ai site.
• Advanced Deep Learning & Reinforcement Learning
• Dropout: A Simple Way to Prevent Neural Networks from Overfitting
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Layer Normalization
• Group Normalization

4. Visual Recognition:

• Convolutional Neural Networks
• CS231n: Convolutional Neural Networks for Visual Recognition
• A guide to convolution aritmetric
• Image classification:
  • Gradient Based Learning Applied to Document Recognition
  • ImageNet Classification with Deep Convolutional Neural Networks
  • Very Deep Convolutional Neural Networks for Large-Scale Image Recognition
  • Going Deeper with Convolutions
  • Deep Residual Learning for Image Recognition
• Object detection:
  • Rich feature hierarchies for accurate object detection and semantic segmentation
  • Fast R-CNN
  • Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
  • You Only Look Once: Unified, Real-Time Object Detection, YOLO v2
  • SSD: Single Shot Multibox Detector
• Image segmentation:
• Image verification:
• Video understanding:

5. Natural Language Processing:

• Sequence models
• CS224n: Natural Language Processing with Deep Learning
• NLP overview: Modern Deep Learning Techniques Applied to NLP
• Fast AI NLP course: Inside you will find the lectures, notebooks and additional resources.
• Jay Alammar Blog: Interesting Illustration of different NLP architectures (Transformers, GPT, BERT, etc)

• Advanced NLP
  • NLP Progress SOTA progress on different NLP tasks for different languages.
  • Harvard NLP
  • Huggingface SOTA pretrained models (Transformers) on different languages.
  • All about Transformers understanding
  • NLP Newsletter

6. Main Low Level tools for Deep Learning:

• TensorFlow
• PyTorch
• Intro to Deep Learning with PyTorch

4. Robotics