Corporate Machine Learning with TensorFlow Training Course

1. What is machine learning?

1. Definition and history
2. Key concepts and terminologies
3. Types of machine learning models

2. Machine learning problems and applications

1. Classification, regression, and clustering problems
2. Impact of machine learning on society

3. Neural networks overview

1. Basics of neural networks
2. Structure and functioning of neurons
3. Layers in neural networks

4. Python machine learning ecosystem: TensorFlow vs scikit-learn

1. Overview of TensorFlow and scikit-learn
2. Key differences and use cases
3. Choosing the right tool for the task

1. Learning and predicting

1. The learning process explained
2. Making predictions with trained models

2. Supervised vs unsupervised learning

1. Differences and applications
2. Examples of both learning types

3. Feature engineering, feature selection, feature scaling

1. Importance of feature engineering
2. Techniques for feature selection and scaling

4. Training data and test data

1. Importance of data splitting

5. Cross-validation

1. Understanding cross-validation
2. Different cross-validation techniques

6. Evaluation metrics

1. Common evaluation metrics for classification and regression
2. Understanding confusion matrix, precision, recall, and F1 score

1. The tf.data API

1. Introduction to tf.data
2. Creating datasets and data pipelines

2. Working with NumPy arrays

1. NumPy arrays in data preprocessing
2. Integration of NumPy with TensorFlow

3. TensorFlow datasets

1. Exploring TensorFlow datasets
2. Loading and preprocessing datasets

1. Choosing a network architecture

1. Criteria for choosing the right architecture
2. Overview of common architectures

2. The tf.keras API

1. Introduction to Keras in TensorFlow
2. Building models with Keras

3. Setting up and compiling a model in TensorFlow

1. Model configuration
2. Compilation options and optimizers

4. Training the model

1. Training processes and techniques
2. Monitoring training progress

5. Model evaluation

1. Evaluating model performance
2. Understanding evaluation metrics

6. Making predictions

1. Generating predictions with trained models
2. Interpreting prediction results

1. Classification: Predicting a label

1. Steps in building a classification model
2. Demo: Simple classification task

2. Text classification with TensorFlow

1. Text preprocessing techniques
2. Building and training a text classification model

3. Image classification with TensorFlow

1. Image data preparation
2. Constructing an image classification model

4. Regression: Predicting a quantity

1. Basics of regression analysis
2. Implementing a regression model in TensorFlow

5. Linear regression with TensorFlow

1. Linear regression fundamentals
2. Building a linear regression model

6. Improving prediction quality

1. Techniques to enhance model predictions
2. Overfitting and underfitting

7. Error analysis

1. Identifying and analyzing model errors
2. Strategies for error reduction

8. Hyper-parameter tuning

1. Importance of hyper-parameter tuning
2. Methods for hyper-parameter optimization