Deep Learning

Generalizing deep learning architectures for natural integration with principles and practice of relational databases. — We got very much used now to read about deep learning, making the headlines with various breakthroughs in research domains ranging from vision and image generation to game playing. However, most of deep learning methods are still quite distant from everyday business practices. A lot of companies successfully transformed into…

Most of the channels in this list are not on other lists from other articles. Before I start, I would like to preface this article by saying that most of these channels are not on other lists. Another thing is that while you watch these channels remember to code along…

1.A memory prosthesis could restore memory in people with damaged brains Link : https://www.technologyreview.com/2022/09/06/1059032/memory-prosthesis-damaged-brains/?utm_source=LinkedIn&utm_campaign=site_visitor.unpaid.engagement&utm_medium=social About : Working with brain stimulation 2. A simpler path to better computer vision Link : https://news.mit.edu/2022/image-programs-data-training-1123 About :

1. Building with nanoparticles, from the bottom up Link : https://news.mit.edu/2022/nanoparticles-printing-silicon-1026 About : Research in working with nanoparticles in terms of arrangement helping with for example Computer Chips 2. New device can control light at unprecedented speeds Link : https://news.mit.edu/2022/control-light-beam-holograms-1128 About : Working with equipments that help to manipulate light

Deep neural networks can take a long time to train. The training speed is affected by the complexity of the architecture, batch size, the GPU used, the size of the training dataset, etc. It may turn out that calculations on the GPU are performed quickly enough, but the data batch…

Similar to AutoML where users don’t rely on their coding experience to build and train ML models, AutoCV is a concept that enables building CV solutions with the least amount of code and the expertise required in CV. Let’s have a look at how this being made possible in today's world. — AI has shown promises. The variety of tasks that it is solving now and will continue to solve in the next 5 or 10 years will also increase exponentially. As such systems evolve, they naturally become more intuitive, normal and easy to use for the public.

A lot of people who get started with learning a convolutional neural network often come across the task of classifying whether an image is of a cat or a dog. Most people are able to build the classifier easily, but have you ever wanted to deploy the network as a…

A few thoughts following David Chalmers’s NeurIPS 2022 talk — I decided last minute (over halfway into its first day) to (virtually) attend the 2022 Conference on Neural Information Processing Systems (NeurIPS). Left on the day’s agenda was David Chalmer’s talk on language models and consciousness (Are Large Language Models Sentient?), which I would have chosen to watch even if…