Shortcut Learning in Deep Neural Networks
This paper establishes a framework for looking at out-of-distribution generalization failures of modern deep learning as the models learning false shortcuts that ...
Yannic Kilcher
Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis
In this video from 2018 Swiss HPC Conference, Torsten Hoefler from (ETH) Zürich presents: Demystifying Parallel and Distributed Deep Learning: An In-Depth ...
InsideHPC Report
Signal Processing and Machine Learning Techniques for Sensor Data Analytics
Free MATLAB Trial: https://goo.gl/yXuXnS Request a Quote: https://goo.gl/wNKDSg Contact Us: https://goo.gl/RjJAkE Learn more about MATLAB: ...
MATLAB
CUDA Neural Networks
CUDA stands for Compute Unified Device Architecture, and it's the reason popular deep learning libraries like Tensorflow & PyTorch are considered ...
Siraj Raval
Lecture 16 | Adversarial Examples and Adversarial Training
In Lecture 16, guest lecturer Ian Goodfellow discusses adversarial examples in deep learning. We discuss why deep networks and other machine learning ...
Stanford University School of Engineering
Lecture 4 | Introduction to Neural Networks
In Lecture 4 we progress from linear classifiers to fully-connected neural networks. We introduce the backpropagation algorithm for computing gradients and ...
Stanford University School of Engineering
HC30-T2: Architectures for Accelerating Deep Neural Nets
Tutorial 2, Hot Chips 30 (2018), Sunday, August 19, 2018. Organizers: Kurt Keutzer, UC Berkeley, Geoffrey Burr, IBM, Bill Dally, Nvidia, and Ralph Wittig, Xilinx ...
hotchipsvideos
What is backpropagation really doing? | Deep learning, chapter 3
What's actually happening to a neural network as it learns? Next video: https://youtu.be/tIeHLnjs5U8 Brought to you by you: http://3b1b.co/nn3-thanks And by ...
3Blue1Brown
Methods and Theory: Inferential Machine Learning - Accelerating Statistical Methodology through ML
RKHS-based tests for Survival Analysis Tamara Fernandez - University College London, United Kingdom Using variational autoencoders to learn efficiently ...
RoyalStatSoc
Accelerating Understanding: Deep Learning, Intelligent Applications, and GPUs
The Institute for Scientific Computing Research (ISCR) sponsored this talk entitled "Deep Learning" on April 16, 2015, at the Lawrence Livermore National ...
Lawrence Livermore National Laboratory
On Gradient-Based Optimization: Accelerated, Stochastic and Nonconvex
Many new theoretical challenges have arisen in the area of gradient-based optimization for large-scale statistical data analysis, driven by the needs of ...
Microsoft Research
Stanford Seminar - Neural Networks on Chip Design from the User Perspective
Yu Wang Tsinghua University October 9, 2019 To apply neural networks to different applications, various customized hardware architectures are proposed in the ...
stanfordonline
"How to run Neural Nets on GPUs' by Melanie Warrick
This talk is just what the title says. I will demonstrate how to run a neural net on a GPU because neural nets are solving some interesting problems and GPUs are ...
Strange Loop
Stanford CS330: Multi-Task and Meta-Learning, 2019 | Lecture 10 - Jeff Clune (Uber AI Labs)
Jeff Clune (Uber AI Labs) Guest Lecture in Stanford CS330 http://cs330.stanford.edu/ To get the latest news on Stanford's upcoming professional programs in ...
stanfordonline
GOTO 2018 • TensorFlow Lite: Accelerate your Android and iOS App with AI • Kaz Sato
This presentation was recorded at GOTO Copenhagen 2018. #GOTOcon #GOTOcph http://gotocph.com Kaz Sato - Staff Developer Advocate, Google Cloud ...
GOTO Conferences
TensorFlow Lite for mobile developers (Google I/O '18)
TensorFlow Lite enables developers to deploy custom machine learning models to mobile devices. This technical session will describe in detail how to take a ...
TensorFlow
"The Decision-Making Side of Machine Learning" with Michael I. Jordan
Title: The Decision-Making Side of Machine Learning: Computational, Inferential, and Economic Perspectives Speaker: Michael I. Jordan Date: March 25, 2020 ...
Association for Computing Machinery (ACM)
Applications of Deep Neural Networks Class Session 5
The fourth class gives an overview of the various backpropagation algorithms that are available for TensorFlow. Jupyter notebooks, data files, and other ...
Jeff Heaton
Lecture 8 | Deep Learning Software
In Lecture 8 we discuss the use of different software packages for deep learning, focusing on TensorFlow and PyTorch. We also discuss some differences ...
Stanford University School of Engineering
End-to-End Learning of Representations for Asynchronous Event-Based Data (ICCV'19)
Event cameras are vision sensors that record asynchronous streams of per-pixel brightness changes, referred to as “events”. They have appealing advantages ...
UZH Robotics and Perception Group
How to Obtain and Run Light and Efficient Deep Learning Networks
Fast growth of the computation cost associated with training and testing of deep neural networks (DNNs) inspired various acceleration techniques. Reducing ...
Microsoft Research
Lecture 2: Machine Learning 1 - Linear Classifiers, SGD | Stanford CS221: AI (Autumn 2019)
Topics: Linear classification, Loss minimization, Stochastic gradient descent Percy Liang, Associate Professor & Dorsa Sadigh, Assistant Professor - Stanford ...
stanfordonline
TensorFlow Lite: Solution for running ML on-device (TF World '19)
TensorFlow Lite is TensorFlow's lightweight cross-platform solution for mobile and embedded devices. It enables on-device machine learning inference with low ...
TensorFlow
Customer Successes with Machine Learning (Google Cloud Next '17)
TensorFlow is rapidly democratizing machine intelligence. Combined with the Google Cloud Machine Learning platform, TensorFlow now allows any developer ...
Google Cloud Platform
The Computing Earthquake: Neural Networks, Cognitive Layering
Abstract A set of profound changes are clearly underway in computing. New computational models like convolutional neural networks for pattern recognition are ...
IEEE Computer Society Silicon Valley
Amazon SageMaker’s Built-in Algorithm Webinar Series: Blazing Text
In this webinar which covers the Blazing Text algorithm used by Amazon SageMaker - https://amzn.to/2S1lZWD, Pratap Ramamurthy, AWS Partner Solution ...
Amazon Web Services
AI for Mobile and IoT Devices: TensorFlow Lite (Google I/O'19)
Imagine building an app that identifies products in real time with your camera or one that responds to voice commands instantly. In this session, you'll learn how ...
TensorFlow
How Graph Technology Is Changing Artificial Intelligence and Machine Learning
Graph enhancements to Artificial Intelligence and Machine Learning are changing the landscape of intelligent applications. Beyond improving accuracy and ...
Neo4j
AWS Builders' Day | Machine Learning: From Notebook to Production with Amazon Sagemaker
See what you can build: https://amzn.to/2ryQs3a Get started with Machine Learning at https://aws.amazon.com/machine-learning/ Amazon AI services bring ...
Amazon Web Services
Deep Learning in Medical Image Diagnostics by Mahesh Balaji at #ODSC_India
Convolutional Neural Networks are revolutionizing the field of Medical Imaging analysis and Computer Aided Diagnostics. Medical images from X-Rays, CT, ...
ConfEngine
CVPR 2019 Oral Session 2-1A: Deep Learning
0:57 Learning Video Representations from Correspondence Proposals Xingyu Liu (Stanford University)*; Joon-Young Lee (Adobe Research); Hailin Jin (Adobe ...
ComputerVisionFoundation Videos
AI at the Edge TensorFlow to TensorRT on Jetson
More resources: https://github.com/NVIDIA-AI-IOT/tf_to_trt_image_classification?nvid=nv-int-jnwrtwtttwhjn-33356, ...
NVIDIA Developer
Unsupervised Contextual Clustering of Abstracts
This study utilizes publicly available data from the National Science Foundation (NSF) Web Application Programming Interface (API). In this paper, various ...
SAS Users
MIT AGI: Artificial General Intelligence
This is the opening lecture for course 6.S099: Artificial General Intelligence. This class is free and open to everyone. Our goal is to take an engineering approach ...
Lex Fridman
Argonne OutLoud: Artificial Intelligence to Accelerate Discovery and Development
Argonne computer scientist Prasanna Balaprakash explains the development, role and importance of AI in science, our understanding of the world, and the ...
Argonne National Laboratory
The Epistemology of Deep Learning - Yann LeCun
Deep Learning: Alchemy or Science? Topic: The Epistemology of Deep Learning Speaker: Yann LeCun Affiliation: Facebook AI Research/New York University ...
Institute for Advanced Study
"Advances in Deep Neural Networks," at ACM Turing 50 Celebration
Deep neural networks can be trained with relatively modest amounts of information and then successfully be applied to large quantities of unstructured data.
Association for Computing Machinery (ACM)
Get Scheduled Predictions on Your ML Models with Amazon SageMaker Batch Transform
Learn more about Amazon SageMaker at – https://amzn.to/2mdzzvF Learn how to generate inferences for an entire dataset with large batches of data, where ...
Amazon Web Services
Efficient and Scalable Deep Learning
In deep learning, researchers keep gaining higher performance by using larger models. However, there are two obstacles blocking the community to build larger ...
Microsoft Research
Gene Instabilities/Accelerated Regions in the Human Genome
Evolution of Human Duplications: Genomic Instability and New Genes (Evan Eichler); Human Accelerated Regions in the Genome (Katherine S. Pollard) ...
University of California Television (UCTV)
Unlocking the power of ML for your JavaScript applications with TensorFlow.js (TF World '19)
TensorFlow.js is a library for training and deploying machine learning models in the browser and in Node.js, and offers unique opportunities for JavaScript ...
TensorFlow
Protein function prediction by neural networks - Cambridge ML Summit ‘19
David Belanger, Google AI, talks about machine learning on proteins and relating protein sequences directly to their functions. Google Developers ML Summit ...
Google Developers
