Deep learning: Challenges in learning and generalization Tomas - PowerPoint PPT Presentation

Deep learning: Challenges in learning and generalization Tomas Mikolov, Facebook AI

What is generalization? Memorization ● to remember all training examples (Universal Approximator) ● 2 + 3 = 5, 3 + 2 = 5, ... Generalization ● to infer novel conclusions ● 123 + 234 = 357, ...

How much do deep neural networks generalize? ● Often less than we would expect (or hope) ● It is easy to make wrong conclusions when using deep networks without understanding how they work ● In this talk: examples of limits of learning in recurrent neural networks

Language Modeling for strong AI ● Language models assign probability to sentences ● P(“Capital city of Czech is Prague”) > P(“Capital city of Czech is Barcelona”) AI-complete problem: ● A bit of progress in language modeling , Joshua Goodman 2001 ● Hutter prize compression challenge

AI-completeness of language modeling We could build intelligent question answering systems and chatbots using perfect language models: ● P(“Is the value of of Pi larger than 3.14? Yes.”) > P(“Is the value of of Pi larger than 3.14? No.”) Language models can generate novel text: ● better language models generate significantly better text (RNNLM, 2010)

Recurrent neural language models ● Breakthrough after 30 years of dominance of n-grams ● The bigger, the better! ○ This continues to be the mainstream even today ● Can this lead to AGI? Strategies for training large scale neural network language models, Mikolov et al, 2011

End-to-end Machine Translation with RNNLM (2012) Simple idea - create a training set from pairs of sentences in different languages: 1. Today it is Sunday. Hoy es domingo. It was sunny yesterday. Ayer estaba soleado. … 2. Train RNNLM 3. Generate continuation of text given only the English sentence: translation!

End-to-end Machine Translation with RNNLM (2012) ● Problem: the performance drops for long sentences ● Even worse: cannot learn identity! ○ Today it is Sunday. Today it is Sunday. It was sunny yesterday. It was sunny yesterday. … ○ Can perfectly memorize training examples, but fails when test data contain longer sequences

Towards RNNs that learn algorithms ● RNNs trained with stochastic gradient descent usually do not learn algorithms ○ just memorize training examples ○ does not matter how many hidden layers we use, and how big the hidden layers are ● This does not have to be a serious problem for applied machine learning ○ memorization is often just fine ● A critical issue for achieving strong AI / AGI

Stack-augmented RNN Inferring algorithmic patterns with stack-augmented recurrent nets, Joulin & Mikolov, 2015

Generalization in RNNs

Binary addition learned with no supervision

Future research - algorithmic transfer learning ● current machine learning models are usually bad at high-level transfer learning ● the “solution” that is learned is often closer to look up table than minimum description length solution ● teaching an RNN to solve a slightly more complex version of already solved task thus mostly fails A roadmap towards machine intelligence, Mikolov et al, 2015

Future research - different approach to learning ● we need much less supervision ● probably no SGD, no convergence (learning never ends) ● maybe more fundamental (basic) model than RNN? ○ are memory, learning, tasks, rewards etc. just emergent properties in a more general system?

Deep learning: Challenges in learning and generalization Tomas - PowerPoint PPT Presentation

Deep learning: Challenges in learning and generalization Tomas Mikolov, Facebook AI What is generalization? Memorization to remember all training examples (Universal Approximator) 2 + 3 = 5, 3 + 2 = 5, ... Generalization to

Towards a Foundation of Deep Learning: SGD, Overparametrization, and Generalization Jason D. Lee

Generalization of Deep Learning 1 Yuan YAO HKUST Some Theories are limited but help:

Assessing Generalization in Deep Reinforcement Learning Soo Jung Jang Background Before (ex:

Structured Losses Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning

Adversarial Training for Deep Learning : A Framework for Improving Robustness, Generalization and

Op#miza#on Challenges for Deep Learning Yoshua Bengio U.

Structured Probabilistic Models for Deep Learning Lecture slides for Chapter 16 of Deep Learning

Loss Valleys and Generalization in Deep Learning Andrew Gordon Wilson Assistant Professor

Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP

Computational Learning Theory: The Theory of Generalization Machine Learning 1 Slides based on

Adaptivity of deep ReLU network and its generalization error analysis Taiji Suzuki The

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice

Disentangling Trainability and Generalization In Deep Neural Networks Lechao Xiao, Je ff rey

Mocha.jl Deep Learning in Julia Chiyuan Zhang (@pluskid) CSAIL, MIT Deep Learning Learning

Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning

Generalization + Globa Image Features Various slides from previous courses by: D.A. Forsyth

Diagnosing ML System Shih-Yang Su Virginia Tech ECE-5424G / CS-5824 Spring 2019 Today's

Outline Learning from Examples 1 Motivation Supervised Learning Aspects of Supervised Learning

Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer NNs

Generalizing CGAL Periodic Delaunay Triangulations Georg Osang , Mael Rouxel-Labb e and Monique

The Landscape of Structural Graph Parameters Michael Lampis KTH Royal Institute of Technology

Lack of Generalization Feature Vectors Rather than use every single detail of a state space, we }

Signed posets and a B -symmetric generalization of Stanleys acyclicity theorem Jake Huryn, Kat