Any fundamental discovery involves a significant degree of risk. If an idea is guaranteed to work then it moves from the realm of research to engineering. Unfortunately, this also means that most…
- Sep. 28 – Oct. 2, 2020
- Lihong Li (Google Brain; chair), Marc G. Bellemare (Google Brain)
- The success of deep neural networks in modeling complicated functions has recently been applied by the reinforcement learning community, resulting in algorithms that are able to learn in environments previously thought to be much too large. Successful applications span domains from robotics to health care. However, the success is not well understood from a theoretical perspective. What are the modeling choices necessary for good performance, and how does the flexibility of deep neural nets help learning? This workshop will connect practitioners to theoreticians with the goal of understanding the most impactful modeling decisions and the properties of deep neural networks that make them so successful. Specifically, we will study the ability of deep neural nets to approximate in the context of reinforcement learning.
The program focused on the following four themes:
- Optimization: How and why can deep models be fit to observed (training) data?
- Generalization: Why do these trained models work well on similar but unobserved (test) data?
- Robustness: How can we analyze and improve the performance of these models when applied outside their intended conditions?
- Generative methods: How can deep learning be used to model probability distributions?
TL;DR: Have you even wondered what is so special about convolution? In this post, I derive the convolution from first principles and show that it naturally emerges from translational symmetry. During…
Have you ever wondered how will the machine learning frameworks of the '20s look like? In this essay, I examine the directions AI research might take and the requirements they impose on the tools at our disposal, concluding with an overview of what I believe to be the two strong candidates: `JAX` and `S4TF`.
Ever since graduation, people have been asking me: “What’s now?” My answer has been an unequivocal: “I don’t know.” I used to think that by the time I finish...
Download Open Datasets on 1000s of Projects + Share Projects on One Platform. Explore Popular Topics Like Government, Sports, Medicine, Fintech, Food, More. Flexible Data Ingestion.
This course will introduce the student to classic neural network structures, Convolution Neural Networks (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Neural Networks (GRU), General Adversarial Networks (GAN) and reinforcement learning. Application of these architectures to computer vision, time series, security, natural language processing (NLP), and data generation will be covered. High Performance Computing (HPC) aspects will demonstrate how deep learning can be leveraged both on graphical processing units (GPUs), as well as grids. Focus is primarily upon the application of deep learning to problems, with some introduction to mathematical foundations. Students will use the Python programming language to implement deep learning using Google TensorFlow and Keras.
Carnegie Mellon University Course: 11-785, Intro to Deep Learning Offering: Fall 2019 Notebook: http://deeplearning.cs.cmu.edu/document/recitation/recitation...
An attempt to create a convenient workspace that makes it possible to work with multiple custom python libraries, while keeping all benefits of Google Colaboratory.
This is a short collection of lessons learned using Colab as my main coding learning environment for the past few months. Some tricks are Colab specific, others as general Jupyter tips, and still more are filesystem related, but all have proven useful for me.
L. Podina, B. Eastman, и M. Kohandel. Proceedings of the 40th International Conference on Machine Learning, том 202 из Proceedings of Machine Learning Research, стр. 27948--27956. PMLR, (23--29 Jul 2023)