Deep Learning Specialization on Coursera
(offered by

A distilled compilation of my notes for Coursera's Deep Learning Specialization (offered by The Deep Learning Specialization is a foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology. In this Specialization, you will build and train neural network architectures such as Convolutional Neural Networks, Recurrent Neural Networks, LSTMs, Transformers, and learn how to make them better with strategies such as Dropout, BatchNorm, Xavier/He initialization, and more. Get ready to master theoretical concepts and their industry applications using Python and TensorFlow and tackle real-world cases such as speech recognition, music synthesis, chatbots, machine translation, natural language processing, and more.
Course 1: Neural Networks and Deep Learning
artificial neural networks; deep learning; backpropagation; python programming
Course 3: Structuring Machine Learning Projects
inductive Transfer; machine learning; multi-task learning; decision-making
Course 4: Convolutional Neural Networks
facial recognition system; convolutional neural network architecture; object detection and segmentation
Course 5: Sequence Models
long short term memory (LSTM); gated recurrent unit (GRU); recurrent neural networks; attention models
Course Info
Topics Covered:
  • Build and train deep neural networks, implement vectorized neural networks, identify architecture parameters, and apply DL to your applications.
  • Use best practices to train and develop test sets and analyze bias/variance for building DL applications, use standard NN techniques, apply optimization algorithms, and implement a neural network in TensorFlow.
  • Use strategies for reducing errors in ML systems, understand complex ML settings, and apply end-to-end, transfer, and multi-task learning.
  • Build a Convolutional Neural Network, apply it to visual detection and recognition tasks, use neural style transfer to generate art, and apply these algorithms to image, video, and other 2D/3D data.
  • Build and train Recurrent Neural Networks and its variants (GRUs, LSTMs), apply RNNs to character-level language modeling, work with NLP and Word Embeddings, and use HuggingFace tokenizers and transformers to perform Named Entity Recognition and Question Answering
The in-line diagrams are taken from Coursera, unless specified otherwise.
If you found our work useful, please cite it as:
  author        = {Chadha, Aman},
  title         = {Distilled Notes for the Deep Learning Specialization on Coursera (offered by},
  howpublished  = {\url{}},
  year          = {2020},
  note          = {Accessed: 2020-07-01},
  url           = {}

A. Chadha, Distilled Notes for the Deep Learning Specialization on Coursera (offered by,, 2020, Accessed: July 1 2020.