Issue #14

September 1, 2019

---

1. 1. Understanding the Different Types of Machine Learning Models [Towards Data Science]
2. 2. In Defense of The Small Social Network [One Zero]
3. 3. To Build Truly Intelligent Machines, Teach Them Cause and Effect [Quanta Magazine]
4. 4. Chris Manning: How computers are learning to understand language [Stanford]
5. 5. Math in Data Science [Dataquest]
6. 6. Linked Lists in Detail with Python Examples: Single Linked Lists [Stack Abuse]
7. 7. Machine Learning for Everyone [vas3k.com]

---

• • Science needs to rethink how it interacts with big data (N. H. Robinson, J. Hamman, R. Abernathey)
• • Deep, Skinny Neural Networks are not Universal Approximators (J. Johnson)
• • Exponential expressivity in deep neural networks through transient chaos (B. Poole, S. Lahiri, M. Raghu, J. Sohl-Dickstein, S. Ganguli)
• • The loss surface and expressivity of deep convolutional neural networks (Q. Nguyen, M. Hein)
• • Network Communities of Dynamical Influence (R. Clark, G. Punzo, M. Macdonald)
• • Superhuman AI for multiplayer poker (N. Brown, T. Sandholm)
• • Deep Learning and MARS: A Connection (M. Kohler, A. Krzyzak, S. Langer)
• • Theoretical Perspectives on Biological Machines (M. L. Mugnai, C. Hyeon, M. Hinczewski, D. Thirumalai)

---