DyCode Engineering - Machine Learning with TensorFlow
0 likes151 views
Machine Learning with TensorFlow is an introduction to machine learning and TensorFlow. It defines machine learning, describes common machine learning categories and algorithms, and focuses on supervised learning. It introduces TensorFlow as a flexible open-source machine learning library, explains key concepts like tensors and computational graphs, and provides demos of linear regression, neural networks, convolutional neural networks, and using TensorFlow and Keras to implement CNNs. Alternatives to TensorFlow are also listed along with references.
![Machine Learning
Machine Learning is the science of getting computers to
learn and act like humans do, and improve their learning
over time in autonomous fashion, by feeding them data
and information in the form of observations and real-
world interactions [1]](https://image.slidesharecdn.com/dycodeengineeringmachinelearningwithtensorflow-180625095651/85/DyCode-Engineering-Machine-Learning-with-TensorFlow-2-320.jpg)
![Linear Regression
Image source: [2]](https://image.slidesharecdn.com/dycodeengineeringmachinelearningwithtensorflow-180625095651/85/DyCode-Engineering-Machine-Learning-with-TensorFlow-12-320.jpg)
![Perceptron
Image source: [2]](https://image.slidesharecdn.com/dycodeengineeringmachinelearningwithtensorflow-180625095651/85/DyCode-Engineering-Machine-Learning-with-TensorFlow-15-320.jpg)
![Multilayer Perceptron
Image source: [2]](https://image.slidesharecdn.com/dycodeengineeringmachinelearningwithtensorflow-180625095651/85/DyCode-Engineering-Machine-Learning-with-TensorFlow-16-320.jpg)
![Convolution
Image source: [2]](https://image.slidesharecdn.com/dycodeengineeringmachinelearningwithtensorflow-180625095651/85/DyCode-Engineering-Machine-Learning-with-TensorFlow-19-320.jpg)
![Convolution
The images illustrates how the change
to parameters affect the output
Image source: [2]](https://image.slidesharecdn.com/dycodeengineeringmachinelearningwithtensorflow-180625095651/85/DyCode-Engineering-Machine-Learning-with-TensorFlow-20-320.jpg)
![Subsampling - pooling
Image source: [2]](https://image.slidesharecdn.com/dycodeengineeringmachinelearningwithtensorflow-180625095651/85/DyCode-Engineering-Machine-Learning-with-TensorFlow-22-320.jpg)
![CNN Architecture: LeNet5
Image source: [2]](https://image.slidesharecdn.com/dycodeengineeringmachinelearningwithtensorflow-180625095651/85/DyCode-Engineering-Machine-Learning-with-TensorFlow-23-320.jpg)
![References
[1] https://www.techemergence.com/what-is-machine-learning/
[2] Bonnin, Rodolfo. Building Machine Learning Projecs with TensorFlow. Packt
Publishing, 2016.
[3] McClure, Nick. TensorFlow Machine Learning Cookbook. Packt Publishing, 2017.](https://image.slidesharecdn.com/dycodeengineeringmachinelearningwithtensorflow-180625095651/85/DyCode-Engineering-Machine-Learning-with-TensorFlow-30-320.jpg)
DyCode Engineering - Machine Learning with TensorFlow
- 2. Machine Learning Machine Learning is the science of getting computers to learn and act like humans do, and improve their learning over time in autonomous fashion, by feeding them data and information in the form of observations and real- world interactions [1]
- 3. Machine Learning Categories Source: MathWorks
- 5. Let's focus on supervised learning
- 6. TensorFlow TensorFlow is fast, flexible, and scalable open-source machine learning library for research and production.
- 7. Key Concepts •TensorFlow bases its data management in tensors •Tensors are manipulated using operations •Each operations are executed in computational graph •Computational graph are executed with CPU, GPU or TPU
- 8. Simple Computation with TF Guess the output!
- 10. What Happened? •Computational graph is not immediately evaluated when they are declared •The graph is executed with tf.Session's run function
- 11. Linear Regression •Predict continuous values from previously acquired data •We try to find linear equation that minimizes the distance between data points and modeled line
- 12. Linear Regression Image source: [2]
- 13. Demo
- 14. Artificial Neural Network •ANN consists of artificial neuron, a mathematical function modeled after a real biological neuron •It receives one or more inputs, and sums them to produce an output •Additionaly, the sums are normally weighted and the sum is passed to a nonlinear function (activation function or transfer function)
- 17. Convolution Neural Network •Part of many of most advanched models currently being employed. •Used in numerous fields, but mainly used in image classifications
- 18. Convolution •Introducing kernel, a m x n-dimensional matrix and is usualy a square matrix (m = n) •Convolution process consist of multiplying the corresponding pixels with the kernel and summing the values for assigning to the central pixel
- 20. Convolution The images illustrates how the change to parameters affect the output Image source: [2]
- 21. Subsampling - pooling •Reduce the quantity and complexity of information while retaining the most important information elements •Well known pooling operations are max pool and average pool
- 22. Subsampling - pooling Image source: [2]
- 23. CNN Architecture: LeNet5 Image source: [2]
- 24. Demo Implementing simple CNN with TensorFlow
- 26. Demo Implementing simple CNN with Keras with TensorFlow as Keras' backend
- 27. The Tools •Anaconda (Python interpreter + libraries for scientific computing) •Jupyter Notebook (comes with Anaconda)
- 29. TensorFlow.js •Available for Node.js and browsers! •High-level APIs similar to Keras!
- 30. References [1] https://www.techemergence.com/what-is-machine-learning/ [2] Bonnin, Rodolfo. Building Machine Learning Projecs with TensorFlow. Packt Publishing, 2016. [3] McClure, Nick. TensorFlow Machine Learning Cookbook. Packt Publishing, 2017.