**Invited Talk:** “A Function Space Characterization of the Learning Dynamics of Gradient Descent” EE Seminar Series, SEAS Dept., Harvard University. November 15, 2019. Video.

**Invited Talk: **“Deep Learning with Domain-Specific Knowledge.” Proceedings of the *2018 Chinese-American Kavli Frontiers of Science Symposium. US and Chinese National Academy of Sciences.* Nanjing, China, October 19-21, 2018.

**Invited Talk: **“Deep Convnets from First Principles: Generative Models, Dynamic Programming and EM”. *Center for Theoretical Biophysics, Rice University,* Houston, TX, February 27, 2018.

**Invited Talk:** “Deep Learning with Domain-Specific Knowledge.”Proceedings of the *2018 Chinese-American Kavli Frontiers of Science Symposium. **US and Chinese* *National Academy of Sciences*. Nanjing, China, October 19-21, 2018.

**Invited Talk:** “A Probabilistic Framework for Deep Learning: Understanding Convnets and Moving Beyond.” *Stanford University*, *Stats 385 Course* from David Donoho. October 2017. Talk Highlights

“A Probabilistic Framework for Deep Learning: Understanding Convnets and Moving Beyond.” *Google Cloud AI Group & Amazon Research*, October 2017.

**Invited Talk:** “A Probabilistic Framework for Deep Learning: Understanding Convnets and Moving Beyond.” Center for Theoretical Neuroscience, Columbia University. NYC, NY, February 17, 2017.

“A Probabilistic Framework for Deep Learning: Understanding Convnets and Moving Beyond.” Seminar Series, Simons Institute. NYC, NY, February 16, 2017.

**Invited Talk: **“Beyond Convnets: The Next-Generation of Highly Scalable Architectures and Unsupervised Learning Algorithms.” *Google Seminar Series on Deep Learning.* Mountain View, California, August 18, 2016.

“A Probabilistic Theory of Deep Learning: How and Why Deep Convnets Work.” In Information Theory & Applications. San Diego, California, February 5, 2016.

“A Probabilistic Theory of Deep Learning: Or How I Learned to Love Neural Nets.” NIPS Workshop on Multi-scale Learning. Montreal Canada, December 2015. (Due to sickness, talk was given by Richard G. Baraniuk instead).

**Invited Talk:** “A Probabilistic Theory of Deep Learning: Applications to Computational Neuroscience.” CBCL Seminar, Tomaso Poggio Lab, Brain and Cognitive Science Dept., MIT. October 2015.

“How and Why Deep Learning Works: Applications to Computational Neuroscience.” Jim DiCarlo Lab, Brain and Cognitive Science Dept., MIT. October 2015.

**Invited Talk:** “How and Why Deep Learning Works” ISS Seminar Series, SEAS Dept., Harvard University. October 2015.

**Invited Talk:** “A Tutorial on Deep Learning: Why Does it Work?” International Conference of Computational Photography. Held at Rice University. April 25, 2015.

# Workshops & Institutes

Frank Noe, **Ankit B. Patel,** Alán Aspuru-Guzik, Katya Scheinberg, Ruth Urner. “From Passive to Active: Generative and Reinforcement Learning with Physics.” Workshop. This workshop is a part of a longer program “Machine Learning for Physics and the Physics of Learning” at the *Institute for Pure and Applied Mathematics (IPAM)* at UCLA.

Richard G. Baraniuk, **Ankit B. Patel, **Anima Anandkumar, Stephane Mallat, nhật Hồ (2018). Integration of Deep Learning Theories. Proceedings of the Conference on Neural Information Processing Systems, 2018. NIPS Workshop

**Accepted to:** “Physics of Hearing: From Neurobiology to Information Theory and Back.” *2018 Kavli Institute of Theoretical Physics.* KITP