Day 6: Continuing to work on my own convolutional neural network

Today I learned how to create a convolutional neural network in python. I used a framework called Pytorch to build the network. I set up the neural net to have three hidden layers. Each node on the hidden layers has its own weights and biases in order to give input to the next layer or provide an output.  In simpler terms a node places its input into a function to generate an output that is used for later nodes. The way a network learns is by evaluating it accuracy after each prediction and updating each nodes function. When building a neural network a data set is necessary. I choose to work with the CIFAR-10 data set. CIFAR-10 contains 10,000 32x32 images of 10 different objects ( plane, car, bird , cat , deer, dog, frog, horse, ship, truck). After training on 9,000 of the images my neural net was able to identify the remaining 1,000 with 60% accuracy. This level of accuracy is certainly not phenomenal but it is very far from random guessing (10%). As I learn more about neural networks I hope to find ways to increase that accuracy.
Image result for neural network visualization hidden layers labeled















Comments

Post a Comment

Popular posts from this blog

Day 11: Network success and an interesting lecture

Image
I started today debugging my code for my neural network. After a healthy amount of googling and some perseverance I was able to roughly train and evaluate my model. The performance was subpar but hopefully I will be able to improve that next week. When that was over I went to the free pizza lunch provided for all of the REU summer research students and I then attended a lecture on visual perception. Although this was not very related to my project I still found it to be a valuable use of my time. It was extremely mind-blowing to realize that our eyes can only see details in a very small field of vision. Our peripheral vision is a lot worse than I previously thought. One of the coolest visual demos was these two tables shown below. Believe it or not the tabletops are exactly the same size and shape. Human visual perception is fascinating and I plan to continue attending the lectures throughout the summer. Source:  http://www.optical-illusionist.com/illusions/table-size-illusio
Read more

Day 26: Polishing my presentation

While I was waiting for my experiments to run on the server I spent the day presenting in front of various members of kLab. I got some very good advice from Dr. Kanan in the morning which I used to update my presentation. Later in the day with the help of  Tyler, Dr. Kemker and Kushal I was able to get a presentation that I was happy with. I plan to update the presentation with the results from the experiments I ran.
Read more

Day 22: Implementing new lifelong learning models

Today I implemented a reservoir sampling algorithm as well as a queue nearest neighbor program. The reservoir algorithm functions similarly to the incremental nearest neighbor program i implemented on Friday. The only difference is that it only holds on to a certain amount of data points per class and when new data points are added it removes an existing point at random. This is an effective way to update your prediction function and it uses less memory than the standard nearest neighbor function. The other program I implemented was the queue nearest neighbor program. This is similar to the reservoir program. The thing queue does differently is that it removes the oldest data point for a specific class when new data points are added. This is also an effective way to reduce memory usage. Tomorrow I plan to combine the VQA data set and these classifiers in order to test the effectiveness of lifelong learning on VQA.
Read more