Kouluttaja: Tarry Singh
AI development in practice with Deep Learning and TensorFlow and Pytorch
- 05.06.2019 - 06.06.2019 Helsinki 1 900 € + alv
This training was ranked #2 in the world out of 8000 trainings, according to the Inc. Magazine. Now it’s available in Helsinki!
Deep Learning is taking with world by storm and technologies such as TensorFlow are empowering the age of Artificial Intelligence. This workshop will teach you from a gentle introduction into Artificial Neural Networks and then it will take you into a deep dive into developing your first Neural Network with TensorFlow already!
The instuctor Tarry Singh is as CEO of deepkapha.ai, a startup focused on advanced AI research for applied AI for enterprises. He has so far trained over 12,000 deep learning engineers himself in classical mode — in corporate enterprises, educational institutions as well as with humanitarian organizations. He is also mentor at Courser’a DeepLearning Specialization working with Andrew Ng, the world’s leading figure in Artificial Intelligence as well
We will also explore the the necessary skill sets required so you can fast track from a novice, whiz past the world of Machine Learning and get a good grip of Deep Learning by understanding how neural networks work.
We will take a look at the use of TensorFlow in your production environments and we will also talk about the many pitfalls and how to avoid them. Topics covered in the two days:
Google Developer Summit on 7th March 2019 is releasing TensorFlow 2.0. Learn from our trainer the key differences difference between TensorFlow 1.x and TensorFlow 2.0 and how you can serve your AI models seamlessly into production.
- Learn about Artificial Intelligence and popular Neural Network Architectures
- Learn about TensorFlow’s Basics (Sessions, Graphs, Variables, Placeholders), TensorFlow’s Framework approach to Neural Network and latest developmentin the upcoming Tensorflow 2.0 version!
- Learn to build your first TensorFlow Neural Network — we build our first AI Neuron (using simple linear fit using 2D data)
- Learn to build your first TensorFlow Neural Network — Image Classification with the famous MNIST Image Dataset OR detect Cats vs Dogs — you pick!
- Learn about use of RNN in Tensorflow and Pytorch — here we will experiment with some genomic or time-series data
- Learning about use of TensorFlow in production — Distributed Computing, Exporting and Serving Models, Additional Tips & Tricks on Model Consstruction and TensorFlow Serving
- Finally as a special bonus for the class — you get to learn and possibly even play with the breakthrough activation function which deepkapha.ai researchers wrote. It’s called ARiA and it has beaten ReLU and Google’s SWiSH function hands-down!
- Wrap up and a surprise Homework Exercise — for those who dare 🙂
Early registrants will get 5 day extra dedicated GPU server provided by deepkapha pre-installed with all latest deep learning libraries for free. You can train your neural network for unlimited hours.
Please, sign up for training well in advance, so that we can ensure you the capacity used in the course by using our learning platform and server.