Search Results for author:
Found 84 papers, 39 papers with code
Many-Shot In-Context Learning
Finally, we demonstrate that, unlike few-shot learning, many-shot learning is effective at overriding pretraining biases and can learn high-dimensional functions with numerical inputs.
Unlearning via Sparse Representations
Machine \emph{unlearning}, which involves erasing knowledge about a \emph{forget set} from a trained model, can prove to be costly and infeasible by existing techniques.
A density estimation perspective on learning from pairwise human preferences
Learning from human feedback (LHF) -- and in particular learning from pairwise preferences -- has recently become a crucial ingredient in training large language models (LLMs), and has been the subject of much research.
SatBird: Bird Species Distribution Modeling with Remote Sensing and Citizen Science Data
The wide availability of remote sensing data and the growing adoption of citizen science tools to collect species observations data at low cost offer an opportunity for improving biodiversity monitoring and enabling the modelling of complex ecosystems.
Bird Distribution Modelling using Remote Sensing and Citizen Science data
Climate change is a major driver of biodiversity loss, changing the geographic range and abundance of many species.
Teaching Algorithmic Reasoning via In-context Learning
Large language models (LLMs) have shown increasing in-context learning capabilities through scaling up model and data size.
Repository-Level Prompt Generation for Large Language Models of Code
With the success of large language models (LLMs) of code and their use as code assistants (e. g. Codex used in GitHub Copilot), techniques for introducing domain-specific knowledge in the prompt design process become important.
Matching Feature Sets for Few-Shot Image Classification
In image classification, it is common practice to train deep networks to extract a single feature vector per input image.
Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions
This presents an interesting machine learning challenge: can we predict runtime errors in a "static" setting, where program execution is not possible?
Fortuitous Forgetting in Connectionist Networks
Forgetting is often seen as an unwanted characteristic in both human and machine learning.
Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning
We propose a method, Head-to-Toe probing (Head2Toe), that selects features from all layers of the source model to train a classification head for the target-domain.
Head2Toe: Utilizing Intermediate Representations for Better OOD Generalization
We propose a method, Head-to-Toe probing (Head2Toe), that selects features from all layers of the source model to train a classification head for the target-domain.
Impact of Aliasing on Generalization in Deep Convolutional Networks
We investigate the impact of aliasing on generalization in Deep Convolutional Networks and show that data augmentation schemes alone are unable to prevent it due to structural limitations in widely used architectures.
Learning to Combine Per-Example Solutions for Neural Program Synthesis
Most learning-based approaches try to find a program that satisfies all examples at once.
Learning a Universal Template for Few-shot Dataset Generalization
Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purpose of training an adaptable model that can then learn classes from new datasets using only a few examples.
Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
To bridge this gap, we perform a cross-family study of the best transfer and meta learners on both a large-scale meta-learning benchmark (Meta-Dataset, MD), and a transfer learning benchmark (Visual Task Adaptation Benchmark, VTAB).
Interpretable Multi-Modal Hate Speech Detection
With growing role of social media in shaping public opinions and beliefs across the world, there has been an increased attention to identify and counter the problem of hate speech on social media.
Self-Supervised Equivariant Scene Synthesis from Video
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into background, characters, and their animations.
Dependency Structure Discovery from Interventions
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.
Learning Flexible Classifiers with Shot-CONditional Episodic (SCONE) Training
We discover that fine-tuning on episodes of a particular shot can specialize the pre-trained model to solving episodes of that shot at the expense of performance on other shots, in agreement with a trade-off recently observed in the context of end-to-end episodic training.
An Effective Anti-Aliasing Approach for Residual Networks
Image pre-processing in the frequency domain has traditionally played a vital role in computer vision and was even part of the standard pipeline in the early days of deep learning.
Learned Equivariant Rendering without Transformation Supervision
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into objects and background.
Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
More practically, we evaluate these models on the task of learning to execute partial programs, as might arise if using the model as a heuristic function in program synthesis.
On-the-Fly Adaptation of Source Code Models
The ability to adapt to unseen, local contexts is an important challenge that successful models of source code must overcome.
Revisiting Fundamentals of Experience Replay
Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understanding.
Learning Graph Structure With A Finite-State Automaton Layer
In practice, edges are used both to represent intrinsic structure (e. g., abstract syntax trees of programs) and more abstract relations that aid reasoning for a downstream task (e. g., results of relevant program analyses).
Uniform Priors for Data-Efficient Transfer
Deep Neural Networks have shown great promise on a variety of downstream applications; but their ability to adapt and generalize to new data and tasks remains a challenge.
A Universal Representation Transformer Layer for Few-Shot Image Classification
We consider the problem of multi-domain few-shot image classification, where unseen classes and examples come from diverse data sources.
Ranked #1 on
Few-Shot Image Classification
on Meta-Dataset Rank
Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)
Reproducibility, that is obtaining similar results as presented in a paper or talk, using the same code and data (when available), is a necessary step to verify the reliability of research findings.
On-the-Fly Adaptation of Source Code Models using Meta-Learning
The ability to adapt to unseen, local contexts is an important challenge that successful models of source code must overcome.
Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling
To make that practical, we show that sampling from this modified density can be achieved by sampling in latent space according to an energy-based model induced by the sum of the latent prior log-density and the discriminator output score.
Diversity inducing Information Bottleneck in Model Ensembles
Although deep learning models have achieved state-of-the-art performance on a number of vision tasks, generalization over high dimensional multi-modal data, and reliable predictive uncertainty estimation are still active areas of research.
Curriculum By Smoothing
We propose to augment the train-ing of CNNs by controlling the amount of high frequency information propagated within the CNNs as training progresses, by convolving the output of a CNN feature map of each layer with a Gaussian kernel.
On Catastrophic Interference in Atari 2600 Games
Our study provides a clear empirical link between catastrophic interference and sample efficiency in reinforcement learning.
Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction
Empirically, we find that these techniques improve the performance of a baseline deep reinforcement learning agent applied to text-based games.
Small-GAN: Speeding Up GAN Training Using Core-sets
Recent work by Brock et al. (2018) suggests that Generative Adversarial Networks (GANs) benefit disproportionately from large mini-batch sizes.
Learning Neural Causal Models from Unknown Interventions
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.
Are Few-shot Learning Benchmarks Too Simple ?
We argue that the widely used Omniglot and miniImageNet benchmarks are too simple because their class semantics do not vary across episodes, which defeats their intended purpose of evaluating few-shot classification methods.
Transfer and Exploration via the Information Bottleneck
In new environments, this model can then identify novel subgoals for further exploration, guiding the agent through a sequence of potential decision states and through new regions of the state space.
A RAD approach to deep mixture models
Flow based models such as Real NVP are an extremely powerful approach to density estimation.
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
Few-shot classification refers to learning a classifier for new classes given only a few examples.
Ranked #7 on
Few-Shot Image Classification
on Meta-Dataset Rank
Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time
We show that several popular few-shot learning benchmarks can be solved with varying degrees of success without using support set Labels at Test-time (LT).
Hyperbolic Discounting and Learning over Multiple Horizons
Reinforcement learning (RL) typically defines a discount factor as part of the Markov Decision Process.
The Hanabi Challenge: A New Frontier for AI Research
From the early days of computing, games have been important testbeds for studying how well machines can do sophisticated decision making.
InfoBot: Transfer and Exploration via the Information Bottleneck
In new environments, this model can then identify novel subgoals for further exploration, guiding the agent through a sequence of potential decision states and through new regions of the state space.
Blindfold Baselines for Embodied QA
We explore blindfold (question-only) baselines for Embodied Question Answering.
Language GANs Falling Short
Generating high-quality text with sufficient diversity is essential for a wide range of Natural Language Generation (NLG) tasks.
Recall Traces: Backtracking Models for Efficient Reinforcement Learning
In many environments only a tiny subset of all states yield high reward.
Meta-Learning for Semi-Supervised Few-Shot Classification
To address this paradigm, we propose novel extensions of Prototypical Networks (Snell et al., 2017) that are augmented with the ability to use unlabeled examples when producing prototypes.
Disentangling the independently controllable factors of variation by interacting with the world
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation.
A Meta-Learning Perspective on Cold-Start Recommendations for Items
Matrix factorization (MF) is one of the most popular techniques for product recommendation, but is known to suffer from serious cold-start problems.
HoME: a Household Multimodal Environment
We introduce HoME: a Household Multimodal Environment for artificial agents to learn from vision, audio, semantics, physics, and interaction with objects and other agents, all within a realistic context.
Multiscale sequence modeling with a learned dictionary
We propose a generalization of neural network sequence models.
Modulating early visual processing by language
It is commonly assumed that language refers to high-level visual concepts while leaving low-level visual processing unaffected.
GuessWhat?! Visual object discovery through multi-modal dialogue
Our key contribution is the collection of a large-scale dataset consisting of 150K human-played games with a total of 800K visual question-answer pairs on 66K images.
Deep learning trends for focal brain pathology segmentation in MRI
In this chapter, we provide a survey of CNN methods applied to medical imaging with a focus on brain pathology segmentation.
Hierarchical Memory Networks
In this paper, we explore a form of hierarchical memory network, which can be considered as a hybrid between hard and soft attention memory networks.
Movie Description
In addition we also collected and aligned movie scripts used in prior work and compare the two sources of descriptions.
Neural Autoregressive Distribution Estimation
We present Neural Autoregressive Distribution Estimation (NADE) models, which are neural network architectures applied to the problem of unsupervised distribution and density estimation.
Recurrent Mixture Density Network for Spatiotemporal Visual Attention
In this work, we propose a spatiotemporal attentional model that learns where to look in a video directly from human fixation data.
Document Neural Autoregressive Distribution Estimation
We present an approach based on feed-forward neural networks for learning the distribution of textual documents.
Autoencoding beyond pixels using a learned similarity metric
We present an autoencoder that leverages learned representations to better measure similarities in data space.
Dynamic Capacity Networks
The low-capacity sub-networks are applied across most of the input, but also provide a guide to select a few portions of the input on which to apply the high-capacity sub-networks.
Within-Brain Classification for Brain Tumor Segmentation
Purpose: In this paper, we investigate a framework for interactive brain tumor segmentation which, at its core, treats the problem of interactive brain tumor segmentation as a machine learning problem.
Clustering is Efficient for Approximate Maximum Inner Product Search
Efficient Maximum Inner Product Search (MIPS) is an important task that has a wide applicability in recommendation systems and classification with a large number of classes.
Domain-Adversarial Training of Neural Networks
Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains.
Ranked #2 on
Domain Adaptation
on Synth Digits-to-SVHN
Brain Tumor Segmentation with Deep Neural Networks
Finally, we explore a cascade architecture in which the output of a basic CNN is treated as an additional source of information for a subsequent CNN.
Ranked #1 on
Brain Tumor Segmentation
on BRATS-2013 leaderboard
Correlational Neural Networks
CCA based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace.
Using Descriptive Video Services to Create a Large Data Source for Video Annotation Research
DVS is an audio narration describing the visual elements and actions in a movie for the visually impaired.
Describing Videos by Exploiting Temporal Structure
In this context, we propose an approach that successfully takes into account both the local and global temporal structure of videos to produce descriptions.
MADE: Masked Autoencoder for Distribution Estimation
There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples.
Ranked #4 on
Density Estimation
on UCI GAS
An Infinite Restricted Boltzmann Machine
We present a mathematical construction for the restricted Boltzmann machine (RBM) that doesn't require specifying the number of hidden units.
Domain-Adversarial Neural Networks
We propose a training objective that implements this idea in the context of a neural network, whose hidden layer is trained to be predictive of the classification task, but uninformative as to the domain of the input.
A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data
Second, we propose a deep extension of our model and provide an efficient way of training the deep model.
Topic Modeling of Multimodal Data: An Autoregressive Approach
Topic modeling based on latent Dirichlet allocation (LDA) has been a framework of choice to deal with multimodal data, such as in image annotation tasks.
An Autoencoder Approach to Learning Bilingual Word Representations
Cross-language learning allows us to use training data from one language to build models for a different language.
Sequential Model-Based Ensemble Optimization
One of the most tedious tasks in the application of machine learning is model selection, i. e. hyperparameter selection.
Learning Multilingual Word Representations using a Bag-of-Words Autoencoder
Recent work on learning multilingual word representations usually relies on the use of word-level alignements (e. g. infered with the help of GIZA++) between translated sentences, in order to align the word embeddings in different languages.
A Deep and Tractable Density Estimator
We can thus use the most convenient model for each inference task at hand, and ensembles of such models with different orderings are immediately available.
Ranked #10 on
Image Generation
on Binarized MNIST
RNADE: The real-valued neural autoregressive density-estimator
We introduce RNADE, a new model for joint density estimation of real-valued vectors.
A Supervised Neural Autoregressive Topic Model for Simultaneous Image Classification and Annotation
Topic modeling based on latent Dirichlet allocation (LDA) has been a framework of choice to perform scene recognition and annotation.
A Neural Autoregressive Topic Model
We describe a new model for learning meaningful representations of text documents from an unlabeled collection of documents.
Practical Bayesian Optimization of Machine Learning Algorithms
In this work, we consider the automatic tuning problem within the framework of Bayesian optimization, in which a learning algorithm's generalization performance is modeled as a sample from a Gaussian process (GP).
Ranked #185 on
Image Classification
on CIFAR-10
Learning to combine foveal glimpses with a third-order Boltzmann machine
We describe a model based on a Boltzmann machine with third-order connections that can learn how to accumulate information about a shape over several fixations.
