In the previous parts, we have taken a look at some supervised neural learning networks with traditional back-propagating feed-forward models, as well as unsupervised neural networks such as the GAN. It can be concluded that the algorithm is no less important than the quantity and quality of the data. Last but not least, there is only one kind of popular learning method I have not delved into yet: Reinforcement Learning (RL).
Perhaps this is the method of machine learning most representative of the concept of learning. To understand this method, it is important to see everything in the…
As far as convolution goes, it has been a great tool for processing existing data. However, it still implies that we must provide a significant amount of data to our robot overlords for them to do any meaningful work.
As efficient as humans can be, collecting loads of good data require massive investments in energy and time. In a modern age where intellectual property is worth billions, there are way too many hurdles to jump over just to obtain some numbers. …
Convolutional Neural Networks are good at abstracting features from an image and using that information to classify and recognize objects of interest in pictures. As the image shrinks in a CNN, only the most important pixels are preserved and the less important are discarded.
They say there is always two sides to everything, this holds true for neural networks too. The convolution doesn’t have to work in only one direction, if we could manage to reverse this process, the practical implications are huge.
So, it’s only natural that after I learn about CNN, I should shift my attention towards the…
The architecture of a neural network is built upon simple connections. Models are based on this idea of relaying information forwards and backwards. Inside each neural network, there is a deep connection between the several layers that are stacked together. Within each neural layer is a simple calculation performed on the data it receives before the data is passed to the next. In this part, we will explore one of the more common layer arrangements in a specific neural network structure called ConvNets. Just like any neural network, it has several hidden layers and an input and output layer.
In my last post, I explored the keras library and studied the concept of a basic model. I also defined and followed the steps to form a model through code.
Taking a step back, that was actually just the tip of the iceberg. It was one way of looking at a model used for deep learning, which is only part of the machine learning tree. But because deep learning falls under this umbrella, it has its advantages.
In many scenarios, concepts from Machine Learning are experimented and explored within deep learning and achieve great results. …
In the last part, I gained some basic insight into the vocabulary used in Machine Learning, and also studied a little about the “Training” process. I learned that “Neural Networks” represent a structured part of Deep Learning, and it revolved around the idea of stacking neural layers together to perform filtering and processing on sets of data, multiple times.
I also talked about Keras, a high-level API which is useful for constructing models for Deep Learning.
Keras believes that User-friendliness and Modularity are what makes a good Deep Learning library, it allows you to experiment and prototype with ideas…
In part 1, I began learning some basic libraries for computer vision, (OpenCV, Numpy) in the hopes that it will help me transition into my company’s workflow. After becoming familiar with the environment, it was clear that my next steps were to start some practice with other libraries related to deep learning.
In particular, TensorFlow. This is because it has been growing in popularity recently and has gathered a visible amount of documentation as well as a community. For a beginner like me, there’s no better way to begin my research
Tensorflow is a library developed by Google, with…
In a world where it’s difficult to avoid the rapid advances of technology, I was among the many who learned to embrace. My name is Amerald, I’m an intern student working at Medmain with the A.I. engineers. This is the story of my ongoing pursuit of machine learning.
As a curious student studying in a modern technological university, the media around me has been popularizing the rise of “Big Data” for quite a while now. In my eyes, this was just a term directly related to the predicted explosion of AI technology that is currently only in its infancy…