The course is part of this learning path
Introduction to Deep Learning
Continue the journey to data and machine learning, with this course from Cloud Academy.
In previous courses, the core principles and foundations of Data and Machine Learning have been covered and best practices explained.
This course gives an informative introduction to deep learning and introducing neural networks.
This course is made up of 12 expertly instructed lectures along with 4 exercises and their respective solutions.
- Understand the core principles of deep learning
- Be able to execute all factors of the framework of neural nets
- It would be advisable to complete the Intro to Data and Machine Learning course before starting.
About the Author
I am a Data Science consultant and trainer. With Catalit I help companies acquire skills and knowledge in data science and harness machine learning and deep learning to reach their goals. With Data Weekends I train people in machine learning, deep learning and big data analytics. I served as lead instructor in Data Science at General Assembly and The Data Incubator and I was Chief Data Officer and co-founder at Spire, a Y-Combinator-backed startup that invented the first consumer wearable device capable of continuously tracking respiration and activity. I earned a joint PhD in biophysics at University of Padua and Université de Paris VI and graduated from Singularity University summer program of 2011.
Hello, and welcome to this video on deep learning successes. In this video, we will review a few successful applications of deep learning and we will highlight a couple of reasons for such a success. Deep learning has won all the most recent competitions on image classification. And by now, it performs better than humans at the task of recognizing objects in an image. It has also been used successfully for image captioning. Which means generating a textual description of the content of the image. All major companies use some form of deep learning for tasks involving speech recognition, speech synthesis, and machine translation.
As far as machine translation is concerned, since deep learning uncodes languages to victorial features, it is even possible to learn translations between pairs of languages on which the model has not been trained. In other words, if the model knows how to translate from German to English. And how to translate from English to Spanish, it would also be able to directly translate from German to Spanish without going through the intermediate English translation.
Deep learning is applied in more and more scientific fields including physics, chemistry, medicine, pharmacology and biology. In these figures, we show some applications in diagnostics. Where deep learning is used to detect skin cancer and eye disease. Another successful application is drug discovery. Where deep learning helps find new uses for existing medicines, shortening by many years the time for a new drug to access the market. Industrial applications of deep learning range from controlling the temperature of data centers to managing crops and agricultural planning. And even to autonomous vehicles. In fact, self-driving car research is no longer available, only to large companies.
Startups are entering the market thanks to how cheap and powerful deep learning is for such systems. Finally, deep reinforcement learning algorithms are learning to play complex games. And they suggest a possible path towards more advanced artificial intelligence. I'd like to emphasis here two characteristics of deep learning models that make them superior to traditional machine learning in many situations. First, the performance of a sufficiently complex deep learning model, will keep increasing as we throw more data at it.
This is different from the behavior of most auto machine learning techniques. Where as the amount of training that increases, the performance of shallow machine learning models will improve after a certain point and then kind of plateau. In contrast, deep learning models will continue to improve as long as the model is deep enough, and there is variety in the training data. Second, deep learning models have tremendously simplified predictive pipelines. Traditional pipelines consisted of feature extraction and model training as separate stat. As we saw in the previous chapter, feature extraction often involved an expert with great domain knowledge and a long time to figure out the features. In contrast, end to end deep learning models are able to learn functions that connect the input data directly to the required output.
Making model development much simpler and faster. In conclusion, deep learning has had successes in many fields including object recognition, text processing, audio processing, time series and games. It's success is connected to its two major factors. First, the performance of deep learning continues to grow as more data is offered for training. And second deep learning models automatically learn good features through representing data. Thank you for watching, and see you in the next video.