# ashishpatel26/andrew-ng-notes

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/ashishpatel26-andrew-ng-notes).**

3,594 stars · 1,233 forks · Jupyter Notebook

## Links

- GitHub: https://github.com/ashishpatel26/Andrew-NG-Notes
- awesome-repositories: https://awesome-repositories.com/repository/ashishpatel26-andrew-ng-notes.md

## Topics

`andrew-ng` `andrew-ng-course` `andrew-ng-machine-learning` `andrewng` `coursera` `coursera-machine-learning` `data-science` `deep-learning` `deep-neural-networks` `dl` `machine-learning` `ml` `neural-network` `neural-networks` `numpy` `pandas` `python` `pytorch` `reinforcement-learning`

## Description

This project is a collection of structured study notes and notebooks serving as an educational resource for deep learning and neural network fundamentals. It provides a technical reference for implementing machine learning theory, covering everything from basic network design to the construction of advanced architectures.

The material specifically focuses on the implementation of convolutional neural networks for computer vision and sequence models for natural language processing. It includes detailed guidance on building object detection systems, face recognition, and speech transcription models, as well as the development of word embeddings and translation mechanisms.

The repository also covers broad capability areas including model optimization, hyperparameter tuning, and error analysis to improve generalization. It addresses various regularization techniques, gradient descent acceleration, and strategies for diagnosing model performance.

The content is delivered through curated notebooks and references focusing on deep learning implementation.

## Tags

### Artificial Intelligence & ML

- [Neural Network Construction](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-construction.md) — Provides a comprehensive guide to designing and building neural network architectures from scratch. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-1-neural-network-deep-learning.md))
- [Supervised Model Weight Optimization](https://awesome-repositories.com/f/artificial-intelligence-ml/supervised-model-weight-optimization.md) — Provides the fundamental implementation of gradient descent for refining neural network weights and biases. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-1-neural-network-deep-learning.md))
- [Attention Mechanisms](https://awesome-repositories.com/f/artificial-intelligence-ml/attention-mechanisms.md) — Implements mathematical and computational attention layers to focus on specific parts of input sequences. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-5-sequence-models.md))
- [Backpropagation](https://awesome-repositories.com/f/artificial-intelligence-ml/backpropagation.md) — Explains the execution of backpropagation to update model parameters and minimize cost. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-1-neural-network-deep-learning.md))
- [Convolutional Neural Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-neural-networks.md) — Provides comprehensive tutorials on building convolutional neural networks for image processing. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-4-convolutional-neural-network.md))
- [Error Analysis Strategies](https://awesome-repositories.com/f/artificial-intelligence-ml/error-analysis-strategies.md) — Compares training and development errors against human-level performance to identify bias or variance. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-3-structuring-ml-projects.md))
- [Gradient Computation](https://awesome-repositories.com/f/artificial-intelligence-ml/gradient-computation.md) — Provides implementation details for calculating gradients via the chain rule to support backpropagation.
- [Sequence Models](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/architectures/sequence-models.md) — Constructs architectures designed for processing ordered data where temporal or sequential dependencies are critical. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-5-sequence-models.md))
- [Educational Neural Network Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/educational-neural-network-implementations.md) — Implements neural network components, including backpropagation and convolutional layers, from first principles for pedagogical purposes.
- [Normalization Layers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/neural-network-layers/normalization-layers.md) — Provides implementations of normalization layers to stabilize hidden layer activations during training. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-2-improving-deep-learning-network.md))
- [Machine Learning Optimization](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-optimization-and-inference/training-algorithms/machine-learning-optimization.md) — Provides a technical reference for optimizing models through hyperparameter tuning and regularization.
- [Hyperparameter Tuning](https://awesome-repositories.com/f/artificial-intelligence-ml/model-fine-tuning-resources/hyperparameter-tuning.md) — Provides techniques for managing and tuning hyperparameters like learning rate and layer depth to optimize performance. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-1-neural-network-deep-learning.md))
- [Hyperparameter Search Strategies](https://awesome-repositories.com/f/artificial-intelligence-ml/model-fine-tuning-resources/hyperparameter-tuning/hyperparameter-search-strategies.md) — Implements optimal model setting searches using grid search, random sampling, and coarse-to-fine sampling schemes. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-2-improving-deep-learning-network.md))
- [Generalization Techniques](https://awesome-repositories.com/f/artificial-intelligence-ml/model-optimization/profiling-and-benchmarking/model-performance-optimization/generalization-techniques.md) — Covers regularization techniques like dropout and L1/L2 norms to improve model generalization. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-2-improving-deep-learning-network.md))
- [Natural Language Processing](https://awesome-repositories.com/f/artificial-intelligence-ml/natural-language-processing.md) — Guides the implementation of NLP workflows, from word embeddings to sequence-to-sequence models.
- [Word Embeddings](https://awesome-repositories.com/f/artificial-intelligence-ml/natural-language-processing/word-embeddings.md) — Implements techniques for creating dense vector representations of words to capture semantic relationships. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-5-sequence-models.md))
- [Adaptive Optimizers](https://awesome-repositories.com/f/artificial-intelligence-ml/optimization-algorithms/adaptive-optimizers.md) — Implements advanced optimization algorithms like Adam and RMSprop to accelerate model convergence. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-2-improving-deep-learning-network.md))
- [Recurrent Neural Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/recurrent-neural-networks.md) — Implements recurrent neural network architectures designed for processing sequential data and time-series prediction. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-5-sequence-models.md))
- [Sequence Learning Models](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-learning-models.md) — Implements architectures for mapping input sequences to output sequences, including recurrent networks and attention. ([source](https://cdn.jsdelivr.net/gh/ashishpatel26/andrew-ng-notes@master/README.md))
- [Mini-Batch Processing](https://awesome-repositories.com/f/artificial-intelligence-ml/training-dataset-processing/mini-batch-processing.md) — Implements mini-batch gradient descent to accelerate training and reduce memory consumption. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-2-improving-deep-learning-network.md))
- [Weight Initialization](https://awesome-repositories.com/f/artificial-intelligence-ml/weight-initialization.md) — Covers weight initialization strategies to break symmetry and prevent activation function saturation in neural networks. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-1-neural-network-deep-learning.md))
- [Activation Functions](https://awesome-repositories.com/f/artificial-intelligence-ml/activation-functions.md) — Implements various non-linear activation functions to prevent signal loss in hidden layers. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-1-neural-network-deep-learning.md))
- [Global Context Attention](https://awesome-repositories.com/f/artificial-intelligence-ml/attention-mechanisms/global-context-attention.md) — Implements attention mechanisms to calculate weighted relevance for sequence generation and translation.
- [Bias and Variance Analysis](https://awesome-repositories.com/f/artificial-intelligence-ml/bias-and-variance-analysis.md) — Explains how to diagnose model performance by analyzing the bias-variance trade-off.
- [Binary Classifiers](https://awesome-repositories.com/f/artificial-intelligence-ml/binary-classifiers.md) — Guides the construction of binary classifiers to map input vectors to binary class probabilities. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-1-neural-network-deep-learning.md))
- [Multiclass](https://awesome-repositories.com/f/artificial-intelligence-ml/classification/multiclass.md) — Implements multiclass classification using softmax regression and one-hot target vectors. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-2-improving-deep-learning-network.md))
- [Object Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/object-detection-tracking/object-detection.md) — Provides guidance on implementing systems that identify and locate multiple objects within images using bounding boxes. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-4-convolutional-neural-network.md))
- [Complexity Reducers](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-neural-networks/complexity-reducers.md) — Explains how to use 1x1 convolutions as complexity reducers to decrease parameter counts and computational cost. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-4-convolutional-neural-network.md))
- [Dataset Splitting Utilities](https://awesome-repositories.com/f/artificial-intelligence-ml/dataset-management/evaluation-datasets/dataset-splitting-utilities.md) — Provides methods for dividing data into training, development, and testing sets for unbiased model evaluation. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-2-improving-deep-learning-network.md))
- [Pooling Layers](https://awesome-repositories.com/f/artificial-intelligence-ml/dimensionality-reduction/pooling-layers.md) — Implements max and average pooling layers to downsample feature maps and increase computational efficiency. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-4-convolutional-neural-network.md))
- [Identity Comparison](https://awesome-repositories.com/f/artificial-intelligence-ml/face-detection/identity-comparison.md) — Implements identity verification by calculating similarity between facial embeddings using Siamese networks. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-4-convolutional-neural-network.md))
- [One-Shot Learning](https://awesome-repositories.com/f/artificial-intelligence-ml/few-shot-learning-baselines/one-shot-learning.md) — Covers techniques for recognizing new categories from a single example using similarity functions and embeddings. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-4-convolutional-neural-network.md))
- [Gated Memory Mechanisms](https://awesome-repositories.com/f/artificial-intelligence-ml/gated-memory-mechanisms.md) — Details the use of forget and update gates in recurrent architectures like LSTMs and GRUs.
- [Multidimensional Convolutional Layers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/neural-network-layers/convolution-layers/1d-convolutional-layers/multidimensional-convolutional-layers.md) — Provides implementation details for applying convolutional operations to 1D audio signals and 3D medical scans. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-4-convolutional-neural-network.md))
- [Data Augmentation](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/data-ingestion-preparation/data-augmentation.md) — Implements techniques to artificially expand training datasets through mirroring, cropping, and rotation. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-4-convolutional-neural-network.md))
- [Gradient Flow Stabilizers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/machine-learning-training/utilities/gradient-optimization-techniques/gradient-flow-stabilizers.md) — Covers weight initialization strategies like He and Xavier to prevent vanishing and exploding gradients. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-2-improving-deep-learning-network.md))
- [Deep Learning Optimization](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-optimization-and-inference/training-algorithms/deep-learning-optimization.md) — Implements optimization algorithms, hyperparameter tuning, and batch normalization to refine model performance. ([source](https://cdn.jsdelivr.net/gh/ashishpatel26/andrew-ng-notes@master/README.md))
- [Bidirectional Recurrent Neural Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/machine-learning-concepts/network-architectures-and-layers/bidirectional-recurrent-neural-networks.md) — Implements recurrent neural networks that process sequences in both forward and backward directions to capture context. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-5-sequence-models.md))
- [Model Evaluation Metrics](https://awesome-repositories.com/f/artificial-intelligence-ml/model-evaluation-metrics.md) — Defines quantitative metrics to measure project success and compare different machine learning algorithms. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-3-structuring-ml-projects.md))
- [Model Performance Analysis](https://awesome-repositories.com/f/artificial-intelligence-ml/model-performance-analysis.md) — Provides tools for evaluating model predictions and diagnosing performance bottlenecks like overfitting. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-2-improving-deep-learning-network.md))
- [Forward Propagation Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/multilayer-perceptrons/forward-propagation-engines.md) — Details the forward propagation process for calculating outputs through successive network layers. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-1-neural-network-deep-learning.md))
- [Neural Style Transfers](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-style-transfers.md) — Demonstrates how to use neural networks to transfer artistic style from a reference image to a content image. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-4-convolutional-neural-network.md))
- [Classification Error Analysis](https://awesome-repositories.com/f/artificial-intelligence-ml/prediction-visualization/accuracy-calculators/error-metrics/classification-error-analysis.md) — Implements manual error analysis by categorizing mislabeled examples to find potential performance ceilings. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-3-structuring-ml-projects.md))
- [Gated Recurrent Units](https://awesome-repositories.com/f/artificial-intelligence-ml/recurrent-neural-networks/gated-recurrent-units.md) — Implements Gated Recurrent Units (GRUs) to manage information flow and mitigate the vanishing gradient problem. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-5-sequence-models.md))
- [Residual Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/residual-networks.md) — Implements skip-connections and residual blocks to prevent vanishing gradients in deep networks.
- [Residual Connection Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/residual-networks/residual-connection-implementations.md) — Provides guidance on implementing skip connections within residual blocks to prevent vanishing gradients in deep networks. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-4-convolutional-neural-network.md))
- [Sequence-to-Sequence Mappings](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-decoding-models/sequence-to-sequence-mappings.md) — Covers the construction of encoder-decoder architectures for sequence mapping tasks.
- [Sequence Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-generation.md) — Demonstrates how to sample new data from trained language models by iteratively predicting the next token. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-5-sequence-models.md))
- [Beam Search Optimizers](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-learning-models/beam-search-optimizers.md) — Implements beam search to optimize the probability of generated sequences in sequence-to-sequence models. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-5-sequence-models.md))
- [Training-Dev Data Distribution Management](https://awesome-repositories.com/f/artificial-intelligence-ml/training-dev-data-distribution-management.md) — Guidance on handling training-dev data mismatch by ensuring consistency across different data distributions. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-3-structuring-ml-projects.md))
- [Transfer Learning](https://awesome-repositories.com/f/artificial-intelligence-ml/transfer-learning.md) — Provides methods for adapting pre-trained models to new tasks by freezing weights and training final layers. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-4-convolutional-neural-network.md))
- [Translation Quality Evaluation](https://awesome-repositories.com/f/artificial-intelligence-ml/translation-quality-evaluation.md) — Provides methods for measuring machine translation quality using metrics like the BLEU score. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-5-sequence-models.md))
- [Convolutional Stride Adjustments](https://awesome-repositories.com/f/artificial-intelligence-ml/transposed-convolutions/upsampling-kernel-initializers/stride-adjusters/convolutional-stride-adjustments.md) — Implements strided convolutions to reduce the spatial dimensions of image representations during feature extraction. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-4-convolutional-neural-network.md))

### Education & Learning Resources

- [Deep Learning Fundamentals](https://awesome-repositories.com/f/education-learning-resources/deep-learning-curriculum/deep-learning-fundamentals.md) — Provides comprehensive educational content covering the core foundations and practical implementations of deep neural networks. ([source](https://cdn.jsdelivr.net/gh/ashishpatel26/andrew-ng-notes@master/README.md))
- [Deep Learning Education](https://awesome-repositories.com/f/education-learning-resources/deep-learning-education.md) — Provides a comprehensive collection of curated notebooks and references for learning neural network theory and practice. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/tree/master/Notebooks))
- [Machine Learning Guides](https://awesome-repositories.com/f/education-learning-resources/machine-learning-guides.md) — Provides a detailed guide on optimization, hyperparameter tuning, and error analysis for improving machine learning model performance.
- [Natural Language Processing Tutorials](https://awesome-repositories.com/f/education-learning-resources/natural-language-processing-tutorials.md) — Provides instructional material on building sequence models for translation and other natural language processing tasks.
- [Machine Learning Education](https://awesome-repositories.com/f/education-learning-resources/educational-resources/systems-applied-computing/machine-learning-education.md) — Provides educational materials on structuring ML projects, defining goals, and managing training and test sets. ([source](https://cdn.jsdelivr.net/gh/ashishpatel26/andrew-ng-notes@master/README.md))
- [Sentiment Classifiers](https://awesome-repositories.com/f/education-learning-resources/educational-resources/systems-applied-computing/machine-learning-education/sentiment-analysis-models/sentiment-classifiers.md) — Provides educational implementations of neural network architectures for classifying text sentiment. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-5-sequence-models.md))
- [Matrix Operations](https://awesome-repositories.com/f/education-learning-resources/matrix-operations.md) — Provides educational implementations of vectorized matrix operations to optimize computational efficiency. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-1-neural-network-deep-learning.md))

### Part of an Awesome List

- [Long Short-Term Memory Networks](https://awesome-repositories.com/f/awesome-lists/ai/neural-network-architectures/long-short-term-memory-networks.md) — Provides implementation guidance for Long Short-Term Memory networks using gated cells to manage sequential data. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-5-sequence-models.md))
- [Sequence To Sequence Models](https://awesome-repositories.com/f/awesome-lists/ai/sequence-to-sequence-models.md) — Implements encoder-decoder architectures to map input sequences to output sequences for tasks like translation. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-5-sequence-models.md))
- [Model Fine-Tuning](https://awesome-repositories.com/f/awesome-lists/ai/model-training-and-fine-tuning/model-fine-tuning.md) — Processes for optimizing pre-trained models on task-specific datasets through fine-tuning. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-3-structuring-ml-projects.md))
- [Deep Learning Resources](https://awesome-repositories.com/f/awesome-lists/ai/deep-learning-resources.md) — Community-curated notes for deep learning specialization courses.
- [Educational Resources](https://awesome-repositories.com/f/awesome-lists/learning/educational-resources.md) — Educational notes based on foundational machine learning courses.

### Data & Databases

- [Feature Scaling](https://awesome-repositories.com/f/data-databases/image-preprocessing-utilities/pixel-normalizers/input-normalizers/feature-scaling.md) — Implements input data normalization to speed up optimization and support higher learning rates. ([source](https://github.com/ashishpatel26/Andrew-NG-Notes/blob/master/andrewng-p-2-improving-deep-learning-network.md))