Final Remarks on the Future of Deep Learning

We have been through a journey together, and if you have read this far you deserve to treat yourself with a nice meal. What you have accomplished deserves recognition. Tell your friends, share what you have learned, and remember to always keep on learning. Deep learning is a rapidly changing field; you cannot sit still. This concluding chapter will briefly present to you some of the new exciting topics and opportunities in deep learning. If you want to continue your learning, we will recommend other helpful resources from Packt that can help you move forward in this field. At the end of this chapter, you will know where to go from here after having learned the basics of deep learning; you will know what other resources Packt offers for you to continue your training in deep learning.

This chapter is organized into the following sections...

Looking for advanced topics in deep learning

The future of deep learning is hard to predict at the moment; things are changing rapidly. However, I believe that if you invest your time in the present advanced topics in deep learning, you might see these areas developing prosperously in the near future.

The following sub-sections discuss some of these advanced topics that have the potential of flourishing and being disruptive in our area.

Deep reinforcement learning

Deep reinforcement learning (DRL) is an area that has gained a lot of attention recently given that deep convolutional networks, and other types of deep networks, have offered solutions to problems that were difficult to solve in the past. Many of the uses of DRL are in areas where we do not have the luxury of having data on all possible conceivable cases, such as space exploration, playing video games, or self-driving cars.

Let's expand on the latter example. If we were using traditional supervised learning to make a...

Learning with more resources from Packt

The following lists of books is not meant to be exhaustive, but a starting point for your next endeavor. These titles have come out at a great time when there is a lot of interest in the field. Regardless of your choice, you will not be disappointed.

Reinforcement learning

• Deep Reinforcement Learning Hands-On - Second Edition, by Maxim Lapan, 2020.
• The Reinforcement Learning Workshop, by Alessandro Palmas et al., 2020.
• Hands-On Reinforcement Learning for Games, by Micheal Lanham, 2020.
• PyTorch 1.x Reinforcement Learning Cookbook, by Yuxi Liu, 2019.
• Python Reinforcement Learning, by Sudharsan Ravichandiran, 2019.
• Reinforcement Learning Algorithms with Python, by Andrea Lonza, 2019.

Self-supervised learning

• The Unsupervised Learning Workshop, by Aaron Jones et. al., 2020.
• Applied Unsupervised Learning with Python, by Benjamin Johnston et. al., 2019.
• Hands-On Unsupervised Learning with Python, by Giuseppe Bonaccorso, 2019.

Summary

This final chapter briefly covered new exciting topics and opportunities in deep learning. We discussed reinforcement learning, self-supervised algorithms, and System 2 algorithms. We also recommended some further resources from Packt, hoping that you will want to continue your learning and move forward in this field. At this point, you should know where to go from here, and be inspired by the future of deep learning. You should be knowledgeable of other recommended books in the area to continue with your learning journey.

You are the future of deep learning, and the future is today. Go ahead and make things happen.

References

• Castro, P. S., Moitra, S., Gelada, C., Kumar, S., and Bellemare, M. G. (2018). Dopamine: A research framework for deep reinforcement learning. arXiv preprint arXiv:1812.06110.
• Kahneman, D. (2011). Thinking, Fast and Slow. Macmillan.
• Sabour, S., Frosst, N., and Hinton, G. E. (2017). Dynamic routing between capsules. In Advances in neural information processing systems (pp. 3856-3866).