# pkmital/tensorflow_tutorials

**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/pkmital-tensorflow-tutorials).**

5,668 stars · 1,161 forks · Jupyter Notebook · NOASSERTION

## Links

- GitHub: https://github.com/pkmital/tensorflow_tutorials
- awesome-repositories: https://awesome-repositories.com/repository/pkmital-tensorflow-tutorials.md

## Description

This project is a collection of educational Jupyter Notebooks providing tutorials on neural network construction and tensor operations using the TensorFlow framework. It serves as a machine learning educational repository and implementation guide for deep learning students.

The suite focuses on specific advanced architectures, including convolutional networks for image classification, residual networks with skip connections for training stability, and variational autoencoders for generative modeling and data synthesis. It also includes guides for building denoising and deep autoencoders to perform feature extraction and dimensionality reduction.

The repository covers a broader surface of predictive modeling, with implementations of linear, polynomial, and logistic regression for predicting continuous values and binary outcomes.

The content is organized into interactive notebooks that allow users to execute mathematical operations and modify machine learning experiments.

## Tags

### Development Tools & Productivity

- [Notebook Execution Environments](https://awesome-repositories.com/f/development-tools-productivity/code-execution-environments/notebook-execution-environments.md) — Organizes educational machine learning experiments within interactive Jupyter notebook execution environments.

### Education & Learning Resources

- [Deep Learning Tutorials](https://awesome-repositories.com/f/education-learning-resources/deep-learning-tutorials.md) — Provides a comprehensive set of interactive tutorials for learning neural network construction using TensorFlow.
- [AI & Machine Learning Education](https://awesome-repositories.com/f/education-learning-resources/technical-domain-education/ai-machine-learning-education.md) — Serves as an educational repository covering neural network theory and practical implementation guides for deep learning.
- [TensorFlow Recipes](https://awesome-repositories.com/f/education-learning-resources/educational-resources/reference-and-media/books-docs-reference/code-examples/tensorflow-recipes.md) — Provides a collection of TensorFlow-focused recipes and examples for building and training machine learning models.
- [Neural Network Implementations](https://awesome-repositories.com/f/education-learning-resources/technical-domain-education/ai-machine-learning-education/neural-network-architectures/linear-neural-networks/neural-network-implementations.md) — Provides instructional guides for building basic and deep neural network architectures from scratch using TensorFlow. ([source](https://github.com/pkmital/tensorflow_tutorials#readme))
- [Computer Vision Tutorials](https://awesome-repositories.com/f/education-learning-resources/computer-vision-tutorials.md) — Offers a practical implementation guide for building image classification and feature extraction models.
- [Generative AI Development Guides](https://awesome-repositories.com/f/education-learning-resources/curricula-instructional-design/curricula-roadmaps/ai-machine-learning-roadmaps/generative-ai-curricula/generative-ai-development-guides.md) — Offers development guides for creating generative models, specifically variational autoencoders for data synthesis.
- [Deep Learning Fundamentals](https://awesome-repositories.com/f/education-learning-resources/deep-learning-curriculum/deep-learning-fundamentals.md) — Teaches foundational deep learning concepts through the definition and execution of tensor graphs.
- [Deep Neural Network Training Optimization](https://awesome-repositories.com/f/education-learning-resources/technical-interview-preparation/ml-interview-preparation/deep-learning-review/deep-neural-network-training-optimization.md) — Implements training optimization techniques including batch normalization and gradient stabilization for deep neural networks. ([source](https://github.com/pkmital/tensorflow_tutorials#readme))
- [Generative Model Examples](https://awesome-repositories.com/f/education-learning-resources/use-case-examples/generative-model-examples.md) — Provides practical implementations of variational networks for content synthesis and latent representation learning.

### Artificial Intelligence & ML

- [Convolutional Neural Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/language-model-integrations/computer-vision-models/convolutional-neural-networks.md) — Builds convolutional neural networks utilizing convolutional layers for feature extraction and visual pattern recognition. ([source](https://github.com/pkmital/tensorflow_tutorials/blob/master/python/05_basic_convnet.py))
- [Computational Graphs](https://awesome-repositories.com/f/artificial-intelligence-ml/computational-graphs.md) — Demonstrates the definition of mathematical operations as computational graphs using TensorFlow tensors.
- [Computer Vision Models](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-models.md) — Develops deep neural networks for image classification and spatial feature extraction.
- [Convolutional Feature Extractors](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-feature-extractors.md) — Implements convolutional feature extraction for spatial pattern recognition in visual image data. ([source](https://github.com/pkmital/tensorflow_tutorials/blob/master/python/01_basics.py))
- [Convolutional Filters](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-filters.md) — Provides tutorials on applying convolutional filters to extract local spatial features from images.
- [Convolutional Autoencoders](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-neural-network-architectures/convolutional-autoencoders.md) — Implements convolutional autoencoders to compress and reconstruct image data using tensor operations. ([source](https://github.com/pkmital/tensorflow_tutorials/blob/master/python/09_convolutional_autoencoder.py))
- [Convolutional Neural Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-neural-networks.md) — Provides tutorials on building convolutional neural networks for processing and recognizing image data. ([source](https://github.com/pkmital/tensorflow_tutorials/blob/master/README.md))
- [Image Classification](https://awesome-repositories.com/f/artificial-intelligence-ml/image-classification.md) — Builds deep networks for image classification using residual connections and batch normalization.
- [Linear and Logistic Regression](https://awesome-repositories.com/f/artificial-intelligence-ml/linear-and-logistic-regression.md) — Implements statistical modeling using linear and logistic functions to predict both numerical and binary outcomes. ([source](https://github.com/pkmital/tensorflow_tutorials/blob/master/README.md))
- [Machine Learning Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning-implementations.md) — Provides code-based reference implementations for constructing various neural network architectures. ([source](https://github.com/pkmital/tensorflow_tutorials#readme))
- [Residual Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-layers/residual-networks.md) — Constructs deep neural networks with skip connections to ensure stable training and prevent gradient loss. ([source](https://github.com/pkmital/tensorflow_tutorials/blob/master/python/10_residual_network.py))
- [Autoencoder Compression](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-model-compression/autoencoder-compression.md) — Provides implementations of autoencoders to compress input data into lower-dimensional latent representations. ([source](https://github.com/pkmital/tensorflow_tutorials/blob/master/python/07_autoencoder.py))
- [Neural Network Model Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-model-implementations.md) — Implements diverse neural network architectures, including convolutional and variational models, for complex data processing. ([source](https://github.com/pkmital/tensorflow_tutorials#readme))
- [Predictive Model Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/numerical-computing-libraries/algorithm-implementations/predictive-model-implementations.md) — Provides coded examples of predictive algorithms, including linear, polynomial, and logistic regression.
- [Polynomial Regression](https://awesome-repositories.com/f/artificial-intelligence-ml/polynomial-regression.md) — Implements polynomial regression models to predict continuous values using non-linear curve fitting.
- [Residual Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/residual-networks.md) — Constructs residual networks with skip connections to prevent vanishing gradients in very deep models.
- [Skip-Connection Architectures](https://awesome-repositories.com/f/artificial-intelligence-ml/skip-connection-architectures.md) — Implements skip-connection architectures to facilitate gradient flow and enable the training of deep networks.
- [Statistical Regression Analysis](https://awesome-repositories.com/f/artificial-intelligence-ml/statistical-regression-analysis.md) — Implements linear and polynomial regression models to analyze relationships between variables. ([source](https://github.com/pkmital/tensorflow_tutorials#readme))
- [Variational Autoencoders](https://awesome-repositories.com/f/artificial-intelligence-ml/variational-autoencoders.md) — Implements variational autoencoders as generative models that learn probabilistic latent spaces for data synthesis. ([source](https://github.com/pkmital/tensorflow_tutorials/blob/master/README.md))
- [Variational Generative Models](https://awesome-repositories.com/f/artificial-intelligence-ml/variational-generative-models.md) — Implements variational generative models that learn data distributions to synthesize new samples.
- [Batch Normalization](https://awesome-repositories.com/f/artificial-intelligence-ml/batch-normalization.md) — Implements batch normalization techniques to stabilize training in deep neural networks.
- [Representation Learning](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-training/representation-learning.md) — Trains neural networks to learn compressed representation embeddings using Gaussian noise in variational autoencoders. ([source](https://github.com/pkmital/tensorflow_tutorials/blob/master/python/11_variational_autoencoder.py))
- [Feature Extraction](https://awesome-repositories.com/f/artificial-intelligence-ml/feature-extraction.md) — Uses autoencoders to extract representative features by compressing high-dimensional data into latent spaces.
- [Latent Space Encoders](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-models/latent-space-generative-models/latent-space-projections/latent-space-encoders.md) — Uses latent space encoders to map high-dimensional input into probabilistic representations for generative reconstruction.
- [Latent Space Compression](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-models/latent-space-generative-models/latent-space-projections/latent-space-encoders/latent-space-compression.md) — Implements encoder-decoder structures for compressing high-dimensional data into latent representations.
- [Logistic Regression Models](https://awesome-repositories.com/f/artificial-intelligence-ml/logistic-regression-models.md) — Creates binary classifiers using logistic regression and the sigmoid function to predict category membership. ([source](https://github.com/pkmital/tensorflow_tutorials#readme))
- [Neural Network Classification](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning-classification/neural-network-classification.md) — Builds supervised learning models using multi-layer perceptrons and logistic regression to categorize input data. ([source](https://github.com/pkmital/tensorflow_tutorials/blob/master/README.md))
- [Model Training Optimizers](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training-optimizers.md) — Applies batch normalization and variational encoding to optimize training convergence and performance. ([source](https://github.com/pkmital/tensorflow_tutorials#readme))
- [Neural Network Architectures](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-architectures.md) — Provides educational content and implementations of complex neural network architectures including residual connections.
- [Regression Analysis](https://awesome-repositories.com/f/artificial-intelligence-ml/regression-analysis.md) — Implements statistical methods for modeling relationships between variables using linear and polynomial techniques. ([source](https://github.com/pkmital/tensorflow_tutorials#readme))
- [Regression Models](https://awesome-repositories.com/f/artificial-intelligence-ml/regression-models.md) — Implements regression models that estimate continuous numeric outcomes based on input features. ([source](https://github.com/pkmital/tensorflow_tutorials/tree/master/notebooks))
- [Weight Tying Strategies](https://awesome-repositories.com/f/artificial-intelligence-ml/weight-tying-strategies.md) — Uses weight tying strategies to share parameters between encoder and decoder layers, reducing model size.

### Part of an Awesome List

- [Denoising Autoencoders](https://awesome-repositories.com/f/awesome-lists/ai/image-reconstruction/denoising-autoencoders.md) — Implements denoising autoencoder architectures trained to recover clean data from corrupted inputs. ([source](https://github.com/pkmital/tensorflow_tutorials/blob/master/python/08_denoising_autoencoder.py))
- [Machine Learning](https://awesome-repositories.com/f/awesome-lists/ai/machine-learning.md) — Provides implementation guides for a wide variety of machine learning models, including classification and regression architectures. ([source](https://github.com/pkmital/tensorflow_tutorials#readme))
- [Deep Learning Models](https://awesome-repositories.com/f/awesome-lists/ai/deep-learning-models.md) — Implements research-grade deep learning architectures, specifically residual networks for improved signal flow. ([source](https://github.com/pkmital/tensorflow_tutorials/tree/master/notebooks))

### Scientific & Mathematical Computing

- [Tensor Computation Graphs](https://awesome-repositories.com/f/scientific-mathematical-computing/high-performance-execution-environments/scientific-computing-platforms/computational-frameworks/tensor-computation-graphs.md) — Defines mathematical operations as directed graphs of tensors to compute numerical results within a managed session. ([source](https://github.com/pkmital/tensorflow_tutorials/blob/master/python/01_basics.py))