I recently acquired a NVidia GTX 970 Founder’s Edition. The device had a damaged fan. As can be clearly seen in the photo, the fan did not sit properly in the mount. This caused the fan to scrape against its metal housing, preventing it from spinning. Actually it’s not clear at all. Nevertheless, the side closest to the camera is higher than the other.
A past blog post explored using multi-layer-perceptrons (MLP) to predict stock prices using Tensorflow and Python. This post introduces another common library used for artificial neural networks (ANN) and other numerical purposes: Theano. An MLP Python class is created implemented using Theano, and then the performance of the class is compared with the TFANN class in a benchmark.
This blog post introduces a type of neural network called a convolutional neural network (CNN) using Python and TensorFlow. A brief introduction to CNNs is given and a helper class for building CNNs in Python and TensorFlow is provided. The source code from this post is available here on GitHub.
This post presents a short script that plots neural network performance on high-dimensional binary data using MatPlotLib in Python. Binary vectors, or vectors only containing 0 and 1, can be useful for representing categorical data or discrete phenomena. The code in this post is available on GitHub.
This post introduces a new program I wrote in Go and C named ShortX. ShortX allows for the creation of keyboard shortcuts that can be used to trigger other keys or commands. The program runs in the background and triggers shortcuts that are specified in a simple ini file.
Expansion is accomplished using low-level Windows API calls so that resource utilization is kept low. ShortX is useful for launching program in Windows, for custom macros in games, and more. Program executables are available on the Software page.
This post is regarding the WPA2 4-way handshake that is used for authentication and the establishment of encryption keys for secure wireless communication. A practical implementation of the key derivation process is provided in python. The sample packet capture containing the 4-way handshake that is used in this post is available here. The complete source code discussed in this post is on Github. The software Wireshark is used to analyze the provided packet trace.
This post revisits the problem of predicting stock prices based on historical stock data using TensorFlow that was explored in a previous post. In the previous post, stock price was predicted solely based on the date. First, the date was converted to a numerical value in LibreOffice, then the resulting integer value was read into a matrix using numpy. As stated in the post, this method was not meant to be indicative of how actual stock prediction is done. This post aims to slightly improve upon the previous model and explore new features in tensorflow and Anaconda python. The corresponding source code is available here.
Note: See a later post Visualizing Neural Network Performance on High-Dimensional Data for code to help visualize neural network learning and performance.