Awesome deep learning
Yeah, I mean it “Awesome!”. Deep learning is the most awesome, exciting, and interesting stuff I feel every data scientist should brag about. When I started my data science journey, I thought Learning basic machine learning was all until I heard about things like neural networks, NLP, Computer vision, and so forth. I was so eager to learn how deep learning works. Along the journey, I realized every business or institution needs artificial intelligence in all their support systems other than staying in the comfort zone of traditional approaches to problem-solving and innovation.
However, getting started can be hectic and overwhelming since resources are all over the web, and getting the right resources can be difficult unless you have someone already practicing it to guide you, else you can waste a lot of time without getting started.
You can imagine what I went through to get started. If you are passionate about deep learning and don’t know where to start, or maybe you’ve started but feel you aren’t understanding anything from some random YouTube videos or resources. This short article is meant for you. Allow me to share with you a few of the facts and resources you need to know about deep learning maybe you could consider making a decision you will never regret today. Deep learning has proved to be the best machine learning technique in different areas all over the world including areas like Natural Language Processing (NLP), Computer Vision, Medicine, Biology, Image generation/enhancement, Recommendation systems, Playing games, Robotics, Other applications – financial and logistical forecasting; text-to-speech; much more.
Many experts will say that to get started with deep learning, you need a lot of math, lots of data, lots of expensive computers, or maybe a Ph.D. Trust me anyone irrespective of any field can practice deep learning. As long as you have an internet connection, you can use many online platforms to run deep learning codes on any computer. A commonly used one is a google Collab notebook. For math, simple high school math is sufficient for anyone to get started. The required basic Linear algebra and calculus can be understood along the way.
If you’ve done some basic machine learning before, the approach to deep learning is almost the same. This however doesn’t imply that deep learning is only for those that have done machine learning before, I have seen experts that have progressed with deep learning minus prior machine learning experience. A critique of basic machine learning is that it mainly involves dealing with quantitative data, unlike most deep learning problems.
Deep learning problems are mostly texts from the web, sound, pictures, and videos among others thus there is always a need to train models that can enable transforming input data into numeric. This is because computers can only understand numbers.
All these applications stipulate why every business or institution needs artificial intelligence in all their support systems other than staying in the comfort zone of traditional approaches to problem-solving and innovation. If this has motivated you, you can check on the following resources which I believe can be a very mounting stone for anyone that would like to embark on a new journey of deep learning.
- link to deep learning for coders(by Jeremy Howard and Sylvain Gugger)
- link to MIT course for deep learning(MIT)
- Link to Coursera deep learning course(by Andrew Ng)
