Machine learning is gradually becoming critical part of life. From recommending movies to self driving cars , AI is making its presence felt in all walks of life.
As ML models are taking critical decision, gradual need was felt to explain the decision taken by these models. Most of these model tend to be black box.
While accurate perdition helps , answer to ‘why it was decided the way it was’ is equally important .
Deep Neural Networks like CNN are extremely versatile and can solve complex problems. But there is a category of problem where they don't perform that well- time series or time series like a problem. In nontechnical language when output (or prediction) of the current step depends on the previous step (or prediction).
Lets' take an example. CNN can classify images as elephants or zebra. Current image classification does not depend on how the previous image was classified.
But for translating German to Tahitian or predicting the daily price of Brent Crude, the sequence is important. …
You only look once (YOLO) is a state-of-the-art, real-time object detection system. It uses convolutional neural network (CNN) for object detection.
Image Classification vs Object Detection
Image classification typically refers to predicting which object is present in image. So input will be set of images contain picture of animals( lets say zebra, tiger and elephant). The output will be classifying it as one of the above animal. The exact position of animal in the image does not matter.
Lets take input image of 28X28. Using RGB scale it the input will be 28X28X3 vector. This will be processes through Convolution…
CNN as defined by Wikipedia
“The name ‘convolutional neural network’ indicates that the network employs a mathematical operation called convolution. Convolutional networks are a specialized type of neural networks that use convolution in place of general matrix multiplication in at least one of their layers.”
To understand CNN , the reader should be familiar with Deep Neural network. Following are references for the same.
Let's take example of image classification to understand how CNN works.
Image can be divided into pixel. Each pixel can numerically be represented using a vector. …
This article is not a deep dive of docker and Kubernetes. This is really a low altitude flight where we look at the container and container orchestration landscape -how its organized, options available.
Containers as defined by GCP- Containers offer a logical packaging mechanism in which applications can be abstracted from the environment in which they actually run.
Container can be assumed as sandbox- its completely isolated from other processes running on the same machine or VM. It has its files system and resources that can not be accessed by other containers on same machine(or on same VM).
What is Cache:
Cache is storing the data reusable data in memory . Normally getting this data is resource intensive and time consuming operation . Once we get data we store it in memory and can be retrieved later when needed.
Typically the resource intensive and time consuming operations are( though not limited to)
We are creating a airline reservation booking website. User can log in and save/edit his details.
User can search and book flights.
This is most common usage of cache that mostly used. In this once we…