Skip to main content

Convolutional Neural Networks - CNNs


Convolution: The primary purpose of Convolution in case of a CNNs is to extract features from the input image. Convolution preserves the spatial relationship between pixels by learning image features


In the computation above we slide the orange matrix over the original image (green) by 1 pixel (also called ‘stride’) and for every position, we compute element wise multiplication (between the two matrices) and add the multiplication outputs to get the final value which forms a single element of the output matrix (pink). Note that the 3×3 matrix “sees” only a part of the input image in each stride.

In CNNs terminology, the 3×3 matrix is called a ‘filter‘ or ‘kernel’ or ‘feature detector’ and the matrix formed by sliding the filter over the image and computing the dot product is called the ‘Convolved Feature’ or ‘Activation Map’ or the ‘Feature Map‘. It is important to note that filters acts as feature detectors from the original input image.


Comments

Popular posts from this blog

Google BigQuery & Apache Hive

Google BIGQUERY is a fast, economical and fully-managed enterprise data warehouse for large-scale data analytics. Details of querying your custom table in BigQuery: https://cloud.google.com/bigquery/quickstart-web-ui The Apache Hive ™ data warehouse software facilitates reading, writing, and managing large datasets residing in distributed storage and queried using SQL syntax. Built on top of Apache Hadoop™, Hive provides the following features: Tools to enable easy access to data via SQL, thus enabling data warehousing tasks such as extract/transform/load (ETL), reporting, and data analysis. A mechanism to impose structure on a variety of data formats Access to files stored either directly in Apache HDFS™ or in other data storage systems such as Apache HBase™ Query execution via Apache Tez™, Apache Spark™, or MapReduce Procedural language with HPL-SQL Sub-second query retrieval via Hive LLAP, Apache YARN and Apache Slider. More details on getting started: 

IIMB PGSEM SOP Essays.

The IIMB PGSEM application for 2008 had a SOP section which required 5 short essays to be written. Here are the ones I had written: Statement of Purpose How do you see the PGSEM helping you in your goals? (150 words) My taking up the PGSEM course has twin objectives, namely, self-development and learning all aspects of setting up, managing a commercial/social enterprise. Having worked in the software industry for five years, I have closely seen the software development life-cycle. However, there are several aspects of business and the economy that are of interest to me and I find the time ripe to explore these in a formal way, through academics; specifically strategic management of a firm, innovation strategies, and the scope of strategic consulting. Getting ready to usher in acceleration in growth opportunities in my care

DNA newspaper plagiarizes my photographs!

The newspaper DNA (Daily News and Analysis - http://www.dnaindia.com/bangalore ) seems to have involved in not verifying its sources of photographs and having used my photographs (does this amount to plagiarism? I think it does) after it carried some of my pictures in the 'After Hrs' section of its newspaper on 31st January 2009, which I had taken at the IIMB Yamini 2009. It is good that they covered the event but they should have cited/verified the sources of the photographs. In all probability they or their sources just picked up the photos from my blog, with the belief that no one would notice anyways - seems they could not escape as luck would have it, I spotted them in the DNA paper on Saturday. It was early in the morning when as I flipped open the last page of the supplement that I was stunned to see my pics, which I was able to recognize immediately - however there were no credits anywhere in sight! Please check the photos below from the e-paper version on their website