1. Understand the difference between supervised, unsupervised and reinforcement learning | Machine Learning 101 | Supervised, Unsupervised, Reinforcement & Beyond (20min) |
2. Watch 3 videos to get a basic understanding on how Artificial Neural Network (ANN) work and how they learn | 1. But what is a Neural Network? (19min) 2. Gradient descent, how neural networks learn (21min) 3. What is backpropagation really doing? (14min) |
3. Understand different topologies of neural networks (e.g. CNN, RNN, LSTM, GRU) | 1. The mostly complete chart of Neural Networks, explained (2 hrs) 2. A deeper understanding of NNets - CNNs (1hr) 3. Recurrent Neural Networks and LSTM (1hr) 4. LSTM by Example using TensorFlow (1hr) |
4. Subscribe and work through the introductory openSAP course on SAP Leonardo Machine Learning Foundation | SAP Leonardo Machine Learning Foundation - An Introduction (1 week with 2-3 h) |
5. Subscribe and work through the detailed openSAP course on Enterprise Deep Learning with TensorFlow | Enterprise Deep Learning with TensorFlow (6 weeks with 3-4h per week) |
6. Attend the course WDEML1 - SAP Leonardo Machine Learning Foundation. As of 2019, this course will be delivered worldwide. | WDEML1 – SAP Leonardo Machine Learning Foundation Workshop (2 days) |
7. Activate your personal SAP Leonardo Machine Learning Foundation environment | Free Trial for SAP Leonardo Machine Learning Foundation if you have a productive account, see Getting Started with SAP Leonardo ML foundation on SAP Cloud Platform |
8. Solve the following Coding Challenge with your ML foundation account. Use the following dataset | 1. Retrain the customizable text classification service of SAP Leonardo Machine Learning Foundation to classify the movie reviews (positive or negative) 2. Build your own neural network that does the same job with at least 80% test accuracy (10% test data) 3. Verify the similarity of two texts (as a whole document) using SAP Leonardo Machine Learning functional services 4. Build a UI that evaluates if two reviews are similar and classifies them as positive or negative using ALL of the networks and services you created earlier |
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
User | Count |
---|---|
21 | |
16 | |
13 | |
12 | |
11 | |
10 | |
7 | |
7 | |
7 | |
7 |