Skip to content

Latest commit

 

History

History
78 lines (42 loc) · 2.62 KB

README.md

File metadata and controls

78 lines (42 loc) · 2.62 KB
Raw

Short Explanation of each LAB

Getting Started with Google Colab:

image https://github.com/GulzhanIsaeva/AI_Midterm_12194812/blob/998f624d526a3d6bf8542bbf69334acc8e9b743c/Week2_lab.ipynb

In the 1st lab I learned how to:

  1. Use Google Colab
  2. Upload the data to Google Colab
  3. Import Kaggle’s dataset
  4. Basic File Operations like "!pip insatall <package_name>" for installing any package

Tensorflow

image

Lab1_1: https://github.com/GulzhanIsaeva/AI_Midterm_12194812/blob/998f624d526a3d6bf8542bbf69334acc8e9b743c/Week5_lab(1_1).ipynb

Lab1_2: https://github.com/GulzhanIsaeva/AI_Midterm_12194812/blob/998f624d526a3d6bf8542bbf69334acc8e9b743c/Week5_lab(1_2).ipynb

Lab1_3: https://github.com/GulzhanIsaeva/AI_Midterm_12194812/blob/998f624d526a3d6bf8542bbf69334acc8e9b743c/Week5_lab(1_3).ipynb

This lab was introduction to Tensorflow and we learned:

  1. What is Tensorflow
  2. Computational graph
  3. Variables, Constants and Placeholders in TensorFlow
  4. Tensorboard visualization
  5. tf.summary.scalar command
  6. tf.summary.histogram command

Linear Regression

image

Lab1: https://github.com/GulzhanIsaeva/AI_Midterm_12194812/blob/998f624d526a3d6bf8542bbf69334acc8e9b743c/Week6_lab(1).ipynb

Lab2: https://github.com/GulzhanIsaeva/AI_Midterm_12194812/blob/998f624d526a3d6bf8542bbf69334acc8e9b743c/Week6_lab(2).ipynb

In the 6th Week Lab's we learned about:

  1. Linear Regression using TensorFlow
  2. Visualization of Linear Regression parameters using TensorFlow
  3. Digit Classification | Neural network to classify MNIST dataset using TensorFlow

Convolutional Neural Networks

image

Lab1: https://github.com/GulzhanIsaeva/AI_Midterm_12194812/blob/f198a5e97921527b4c4ece4f5b4cc7d698b05c09/Week7_lab(1).ipynb

Lab2: https://github.com/GulzhanIsaeva/AI_Midterm_12194812/blob/f198a5e97921527b4c4ece4f5b4cc7d698b05c09/Week7_lab(2).ipynb

7th Week Lab Contents was as follows:

  1. Convolutional Neural Networks
  2. The CIFAR-10 Dataset
  3. Characteristics and building blocks for convolutional layers
  4. Combining feature maps into a convolutional layer
  5. Combining convolutional and fully connected layers into a networ
  6. kEffects of sparse connections and weight sharing
  7. Image classification with a convolutional network