Day 5: Beginning to create my own convolutional neural network

At the start of today I watched 2 of Stanford's lectures one on feed-forward neural networks and the other on convolutional neural networks. In a feed-forward network there is no connection to previous nodes. This is a great visualization of the relationship between nodes and how a previous layer provides input for a future layer. The other type of neural network is a recurrent neural network. What makes a recurrent network different is that outputs on a certain layer can act as inputs for the previous layer. I have not gone into depth on recurrent networks so my knowledge is limited. A convolutional network is not another type of network but rather a specific layer on a neural network which alters the data. One example of convolution is pooling. As demonstrated below pooling takes a filter full of values and then averages or sums them creating a new array. Pooling is useful because it reduces the size of your matrix while retaining a similar value. This allows for calculations to be performed quicker. I will continue to build my own convolutional neural net over the next week.


Image result for pooling machine learning gif
Source: https://hackernoon.com/visualizing-parts-of-convolutional-neural-networks-using-keras-and-cats-5cc01b214e59

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