Download as PDF, PPTX
Uploaded byAfif Akbar Iskandar
Deep Learning for Industry
1. Deep learning uses neural networks with multiple layers of nodes between the input and output to perform feature identification and processing in stages, similar to the human brain. 2. Recent advances in algorithms allow for training deep neural networks with many layers, which was previously difficult. 3. Deep learning has applications in image recognition, speech recognition, bioinformatics, data mining, and more by automatically learning complex patterns in large datasets to perform tasks like object detection and customer classification.
Deep Learning for Industry
- 1. 1 Deep Learning Application forIndustry Afif A. Iskandar
- 2.
- 3.
- 4. 4 What is DeepLearning ? So, 1. what exactly is deep learning ? And, 2. why is it generally better than other methods on image, speech and certain other types of data?
- 5. 5 So, 1. whatexactly is deep learning ? And, 2. why is it generally better than other methods on image, speech and certain other types of data? The short answers 1. ‘Deep Learning’ means using a neural network with several layers of nodes between input and output 2. the series of layers between input & output do feature identification and processing in a series of stages, just as our brains seem to.
- 6. 6 hmmm… OK, but: 3.multilayer neural networks have been around for 25 years. What’s actually new?
- 7. 7 hmmm… OK, but: 3.multilayer neural networks have been around for 25 years. What’s actually new? we have always had good algorithms for learning the weights in networks with 1 hidden layer but these algorithms are not good at learning the weights for networks with more hidden layers what’s new is: algorithms for training many-later networks
- 8. 8 Longer Answer 1. reminder/quick-explanationof how neural network weights are learned; 2. the idea of unsupervised feature learning (why ‘intermediate features’ are important for difficult classification tasks, and how NNs seem to naturally learn them) 3. The ‘breakthrough’ – the simple trick for training Deep neural networks
- 9.
- 10. 10 Deep Learning andOld Algorithm Comparison
- 11.
- 12. 12 Why do weneed learning? • Computers need functions that map highly variable data: ⬥ Speech recognition: Audio signal -> words ⬥ Image analysis: Video signal -> objects ⬥ Bio-Informatics: Micro-array Images -> gene function ⬥ Data Mining: Transaction logs -> customer classification • For accuracy, functions must be tuned to fit the data source. • For real-time processing, function computation has to be very fast.
- 13. 13 Theory Vs. Practice •Theoretician: I want a polynomial-time algorithm which is guaranteed to perform arbitrarily well in “all” situations. - I prove theorems. • Practitioner: I want a real-time algorithm that performs well on my problem. - I experiment. • My approach: I want combining algorithms whose performance and speed is guaranteed relative to the performance and speed of their components. - I do both.
- 14. 14 Deep Learning :Training
- 15.
- 16.
- 17.
- 18.
- 19. 19 Challenge ▪ Resources (DeepLearning Engineer) ▪ Investment (Time and Money for Deep Learning Research)
- 20. 20 Interested about DeepLearning ? ▪ Siraj Raval Channel ▪ http://deeplearning.net/ ▪ Udemy Courses