Week 2:

Lab Contents:

• Getting started with Google Colab

• Uploading data

• Importing Kaggle’s dataset

• Basic File Operations

https://github.com/tosmeley/project_folder/blob/main/week_2.ipynb https://github.com/tosmeley/project_folder/blob/main/week_2_part_2.ipynb

Week 5:

Lab Contents:

• Computational graph

• Variables, Constants and Placeholder in TensorFlow

• Tensorboard visualization

• f.summary.scalar command

• Tf.summary.histogram command

https://github.com/tosmeley/project_folder/blob/main/Intro.ipynb https://github.com/tosmeley/project_folder/blob/main/Intro1.ipynb https://github.com/tosmeley/project_folder/blob/main/Intro_to_Colab.ipynb

Week 6:

Lab Contents: **

• Linear Regression using TensorFlow

• Visualization of Linear Regression parameters using TensorFlow

• Digit Classification | Neural network to classify MNIST dataset using TensorFlow

• Image Denoising using Neural Network

https://github.com/tosmeley/project_folder/blob/main/week_6_lab_2.ipynb https://github.com/tosmeley/project_folder/blob/main/week_6_tuesday_tensorflow_tuesday_excercise_2_.ipynb https://github.com/tosmeley/project_folder/blob/main/week_6_tensorflow.ipynb

Week 7:

Lab Contents: **

• Convolutional Neural Networks

• The CIFAR-10 Dataset

• Characteristics and building blocks for convolutional layers

• Combining feature maps into a convolutional layer

• Combining convolutional and fully connected layers into a network

• Effects of sparse connections and weight sharing

• Image classification with a convolutional network

https://github.com/tosmeley/project_folder/blob/main/week_7_tuesday_.ipynb

Week 9:

Lab Contents: Logistic unit for binary classification

• Softmax unit for multiclass classification

• Linear unit for regression

• The Boston Housing dataset

• Predicting house prices with a DNN

• Improving generalization with regularization

• Experiment: Deeper and regularized models for house price prediction

• Concluding remarks on output units and regression problems

  https://github.com/tosmeley/project_folder/blob/main/week_9_tuesday.ipynb https://github.com/tosmeley/project_folder/blob/main/week_9_wednesday_.ipynb

Week 10:

Lab Contents:

• VGGNet
• GoogLeNet
• ResNet
• Transfer Learning
• Data Augmentation as a Regularization Technique
• Mistakes made by CNNs
• Reducing parameters with Depthwise Separable Convolution
• Striking the right network design balance with
• EfficientNet

https://github.com/tosmeley/project_folder/blob/main/week_10_wednesday.ipynb

Week 11:

Lab Contents:

• Limitations of Feedforward Networks
• Recurrent Neural Networks
• Mathematical Representation of a Recurrent layer
• Combining layers into an RNN
• Alternative veiw of RNN and Unrolling in Time
• Backpropagation Through Time
• Programming Example: Forecasting book sales

https://github.com/tosmeley/project_folder/blob/main/week_11.ipynb

Week 12:

Lab Contents:

• Keeping Gradients Healthy
• Introduction to LSTM
• Creating a network of LSTM cells
• Alternative view of LSTM

https://github.com/tosmeley/project_folder/blob/main/week_12_.ipynb

Week 13:

Lab Contents:

• Encoding text
• Longer-term prediction and autoregressive models
• Beam Search
• Bidirectional RNNS
• Different combinations of input and output sequences

https://github.com/tosmeley/project_folder/blob/main/week_13.ipynb

https://github.com/tosmeley/project_folder/blob/main/week_13_wednesday.ipynb

Week 14:

Lab Contents:

• Natural Language Processing using transformer encoder

https://github.com/tosmeley/project_folder/blob/main/week_14_.ipynb