Pre Deep Learning&Applied AI Study Group Reading List

This is a curated list intended for prospective participants of inzva Deeplearning.ai Study Group and the Applied AI Study group to check out before beginning their journey.

Knowing what is in these readings will help you earn the necessary prerequisites and raise your chances to get accepted. If you already applied, please check these selected study materials before the start date to make sure you are ready for the programs.

Cheers from the inzva AI team!

Selected Materials to study before Deeplearning.ai Study Group

1. For stronger mathematical background: MIT Linear Algebra Lectures by Gilbert Strang (first 4 videos are enough)

   • https://www.youtube.com/watch?v=ZK3O402wf1c&list=PL49CF3715CB9EF31D

2. More mathematics: Matrix Calculus You Need for Deep Learning

   • https://explained.ai/matrix-calculus/index.html

3. Vital background to machine learning: Introduction to Probability and Statistics (MIT)

   • https://www.edx.org/course/probability-the-science-of-uncertainty-and-data

4. To get used to the machine learning by Introduction to Machine Learning (Coursera), it is also an introduction to Andrew Ng :))

   • https://www.coursera.org/learn/machine-learning

5. To learn more about machine learning (Unsupervised, supervised, reinforcement)

   • https://datascience.berkeley.edu/blog/what-is-machine-learning/

   • https://towardsdatascience.com/introducing-deep-learning-and-neural-networks-deep-learning-for-rookies-1-bd68f9cf5883

6. To find out the answer to “What is a Neural Network?” by the amazing Youtube video series by 3Blue1Brown (4 videos)

   • https://www.youtube.com/watch?v=aircAruvnKk&list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi

7. A basic review of Deep Learning

   • https://www.cs.toronto.edu/~hinton/absps/NatureDeepReview.pdf

8. To visualize a neural network and play with it: Google DL visualization

Selected Materials to study before Applied AI Study Group

1. You can check out the previous batches’ codes from here:

• https://github.com/inzva/Applied-AI-Study-Group

2. Here are some examples of the preprocessing stages of different types of datasets:

a.Image

• https://towardsdatascience.com/image-pre-processing-c1aec0be3edf

b.Text

• https://towardsdatascience.com/nlp-for-beginners-cleaning-preprocessing-text-data-ae8e306bef0f

c.Structured data (CSV)

• https://medium.com/analytics-vidhya/build-your-first-neural-network-model-on-a-structured-dataset-using-keras-d9e7de5c6724

• https://data-flair.training/blogs/python-ml-data-preprocessing/

3. Problems and solutions on Titanic data in Kaggle 

• https://www.kaggle.com/startupsci/titanic-data-science-solutions

4. Here are some basic introductory tutorials for PyTorch, Tensorflow, and Keras

a.https://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html

b.MNIST Classification

• https://medium.com/@mjbhobe/mnist-digits-classification-with-keras-ed6c2374bd0e

c.Sentiment Analysis

• https://medium.com/datadriveninvestor/deep-learning-lstm-for-sentiment-analysis-in-tensorflow-with-keras-api-92e62cde7626

d.Classification on Iris Dataset

• https://www.tensorflow.org/tutorials/customization/custom_training_walkthrough

e.Regression on Titanic Dataset

• https://www.tensorflow.org/tutorials/estimator/linear

5.Ready-to-use datasets in Keras that you can play around with:

• https://keras.io/datasets/

6. A bit more challenging reading (understanding RNNs and Transformers)

• http://karpathy.github.io/2015/05/21/rnn-effectiveness/

• http://jalammar.github.io/illustrated-transformer/

7. Interesting (and valuable) papers to read for the ones who are looking for more challenges:

a. Two-Stream Convolutional Networks for Action Recognition in Videos:

• http://papers.nips.cc/paper/5353-two-stream-convolutional-networks-for-action-recognition-in-videos.pdf

b.Image Super-Resolution Using Deep Convolutional Networks:

• https://arxiv.org/pdf/1501.00092v3.pdf

c.A Neural Algorithm of Artistic Style:

• https://arxiv.org/pdf/1508.06576.pdf

d.Distributed Representations of Words and Phrases and their Compositionality:

• https://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf

e.Rethinking the inception architecture for computer vision:

• http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Szegedy_Rethinking_the_Inception_CVPR_2016_paper.pdf

f.Deep speech 2: End-to-end speech recognition in English and Mandarin:

• https://arxiv.org/pdf/1512.02595

g.WaveNet: A Generative Model for Raw Audio:

• https://arxiv.org/pdf/1609.03499v2