tf-exam-revision

Revising Stuff for upcoming TF Certification

Referred Course : https://www.coursera.org/specializations/tensorflow-in-practice?

Find my Certification Here : https://www.coursera.org/account/accomplishments/specialization/certificate/XL2HJCNCDJMZ

Contents

• Course-1 (Introduction to Tensorflow for AI, ML and DL)

  • House Price Prediction.
    • Simple X->Y Mapping.
  • HandWriting Recognition using MNIST.
    • Used Deep Neural Network.
    • Used Convolutional Neural Network.
    • Used Callbacks.
    • Pre-processing Data.
    • Multi-Class Classification.
  • Fashion Outfit Classifier using FashionMNIST.
    • Used Deep Neural Network.
    • Used Convolutional Neural Network.
    • Used Callbacks.
    • Pre-processing Data.
    • Multi-Class Classification.
  • Horses-vs-Humans Classification using Kaggle Dataset.
    • Used Deep Neural Network.
    • Used Convolutional Neural Network.
    • Used Callbacks.
    • Pre-processing Data.
    • Binary Classification.
    • Used various Augmentation Techniques.
  • Cats-vs-Dogs Classification using Kaggle Dataset.
    • Used Deep Neural Network.
    • Used Convolutional Neural Network.
    • Used Callbacks.
    • Pre-processing Data.
    • Binary Classification.
    • Used various Augmentation Techniques.

• Course - 2 (Convolutional Neural Networks)

  • Visualizing Effect of Convolutions layer by layer.
    • Get Outputs and Inputs of the Layers.
    • Define a Visualization model.
    • Image Processing based on input of the model.
    • Define a display grid according to feature size.
    • Plot the layer by layer output of convolutions.
  • Transfer Learning
    • Used Inception v3 as a base model and finetuned it with Horses-vs-Humans Dataset.
  • Multi-Class Classification
    • Classifying Rock Paper Scissors Dataset.

• Course - 3 NLP (Will continue at last)

• Course - 4 Sequences, Time Series and Forecasting

  • Exercise - 1 Simple MA, Differencing and Naive Forecasting
  • Exercise - 2 Neural Netword based Forcasting

Checklist

• Build and train neural network models using TensorFlow 2.x
  • Use TensorFlow 2.x
  • Build, compile and train machine learning (ML) models using TensorFlow
  • Preprocess data to get it ready for use in a model.
  • Use models to predict results.
  • Build sequential models with multiple layers.
  • Build and train models for binary classification.
  • Build and train models for multi-class categorization.
  • Plot loss and accuracy of a trained model.
  • Identify strategies to prevent overfitting, including augmentation and dropout.
  • Use pretrained models (transfer learning).
  • Extract features from pre-trained models.
  • Ensure that inputs to a model are in the correct shape.
  • Ensure that you can match test data to the input shape of a neural network.
  • Ensure you can match output data of a neural network to specified input shape for test data.
  • Understand batch loading of data.
  • Use callbacks to trigger the end of training cycles.
  • Use datasets from different sources.
  • Use datasets in different formats, including json and csv.
  • Use datasets from tf.data.datasets.
• Image classification
  • Define Convolutional neural networks with Conv2D and pooling layers.
  • Build and train models to process real-world image datasets.
  • Understand how to use convolutions to improve your neural network.
  • Use real-world images in different shapes and sizes.
  • Use image augmentation to prevent overfitting.
  • Use ImageDataGenerator.
  • Understand how ImageDataGenerator labels images based on the directory structure.
• Natural language processing (NLP)
  • Build natural language processing systems using TensorFlow.
  • Prepare text to use in TensorFlow models.
  • Build models that identify the category of a piece of text using binary categorization.
  • Build models that identify the category of a piece of text using multi-class categorization.
  • Use word embeddings in your TensorFlow model.
  • Use LSTMs in your model to classify text for either binary or multi-class categorization.
  • Add RNN and GRU layers to your model.
  • Use RNNS, LSTMs, GRUs and CNNs in models that work with text.
  • Train LSTMs on existing text to generate text (such as songs and poetry).
• Time series, sequences and predictions
  • Train, tune and use time series, sequence and prediction models.
  • Prepare data for time series learning.
  • Understand Mean Average Error (MAE) and how it can be used to evaluate accuracy of sequence models.
  • Use RNNs and CNNs for time series, sequence and forecasting models.
  • Identify when to use trailing versus centred windows.
  • Use TensorFlow for forecasting.
  • Prepare features and labels.
  • Identify and compensate for sequence bias.
  • Adjust the learning rate dynamically in time series, sequence and prediction models.