Search Results for author:
Found 47 papers, 19 papers with code
Learning and Unlearning of Fabricated Knowledge in Language Models
What happens when a new piece of knowledge is introduced into the training data and how long does it last while a large language model (LM) continues to train?
Towards Efficient Modelling of String Dynamics: A Comparison of State Space and Koopman based Deep Learning Methods
This paper presents an examination of State Space Models (SSM) and Koopman-based deep learning methods for modelling the dynamics of both linear and non-linear stiff strings.
Narrowing the Focus: Learned Optimizers for Pretrained Models
In modern deep learning, the models are learned by applying gradient updates using an optimizer, which transforms the updates based on various statistics.
Linear Transformers are Versatile In-Context Learners
In this paper, we prove that each layer of a linear transformer maintains a weight vector for an implicit linear regression problem and can be interpreted as performing a variant of preconditioned gradient descent.
FM Tone Transfer with Envelope Learning
Tone Transfer is a novel deep-learning technique for interfacing a sound source with a synthesizer, transforming the timbre of audio excerpts while keeping their musical form content.
Uncovering mesa-optimization algorithms in Transformers
Some autoregressive models exhibit in-context learning capabilities: being able to learn as an input sequence is processed, without undergoing any parameter changes, and without being explicitly trained to do so.
Continual HyperTransformer: A Meta-Learner for Continual Few-Shot Learning
We focus on the problem of learning without forgetting from multiple tasks arriving sequentially, where each task is defined using a few-shot episode of novel or already seen classes.
Training trajectories, mini-batch losses and the curious role of the learning rate
In particular, for Exponential Moving Average (EMA) and Stochastic Weight Averaging we show that our proposed model matches the observed training trajectories on ImageNet.
Decentralized Learning with Multi-Headed Distillation
We study the effects of data and model architecture heterogeneity and the impact of the underlying communication graph topology on learning efficiency and show that our agents can significantly improve their performance compared to learning in isolation.
Rigid-Body Sound Synthesis with Differentiable Modal Resonators
Physical models of rigid bodies are used for sound synthesis in applications from virtual environments to music production.
DDX7: Differentiable FM Synthesis of Musical Instrument Sounds
The training process involves a corpus of audio for supervision, and spectral reconstruction loss functions.
Anomalous behaviour in loss-gradient based interpretability methods
Loss-gradients are used to interpret the decision making process of deep learning models.
Deep Embeddings for Robust User-Based Amateur Vocal Percussion Classification
Vocal Percussion Transcription (VPT) is concerned with the automatic detection and classification of vocal percussion sound events, allowing music creators and producers to sketch drum lines on the fly.
Deep Conditional Representation Learning for Drum Sample Retrieval by Vocalisation
Imitating musical instruments with the human voice is an efficient way of communicating ideas between music producers, from sketching melody lines to clarifying desired sonorities.
Fine-tuning Image Transformers using Learnable Memory
In this paper we propose augmenting Vision Transformer models with learnable memory tokens.
HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning
In this work we propose a HyperTransformer, a Transformer-based model for supervised and semi-supervised few-shot learning that generates weights of a convolutional neural network (CNN) directly from support samples.
HyperTransformer: Attention-Based CNN Model Generation from Few Samples
In this work we propose a HyperTransformer, a transformer based model that generates all weights of a CNN model directly from the support samples.
Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks
From practical perspective, our approach allows to: (a) reuse existing modules for learning new task by adjusting the computation order, (b) use it for unsupervised multi-source domain adaptation to illustrate that adaptation to unseen data can be achieved by only manipulating the order of pretrained modules, (c) show how our approach can be used to increase accuracy of existing architectures for image classification tasks such as ImageNet, without any parameter increase, by reusing the same block multiple times.
Meta-Learning Bidirectional Update Rules
We show that classical gradient-based backpropagation in neural networks can be seen as a special case of a two-state network where one state is used for activations and another for gradients, with update rules derived from the chain rule.
SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
In this paper we address the question: can task-specific detectors be trained and represented as a shared set of weights, plus a very small set of additional weights for each task?
Large-Scale Generative Data-Free Distillation
Knowledge distillation is one of the most popular and effective techniques for knowledge transfer, model compression and semi-supervised learning.
Image segmentation via Cellular Automata
The update rule is applied repeatedly in parallel to a large random subset of cells and after convergence is used to produce segmentation masks that are then back-propagated to learn the optimal update rules using standard gradient descent methods.
Structured Multi-Hashing for Model Compression
Despite the success of deep neural networks (DNNs), state-of-the-art models are too large to deploy on low-resource devices or common server configurations in which multiple models are held in memory.
Non-discriminative data or weak model? On the relative importance of data and model resolution
We explore the question of how the resolution of the input image ("input resolution") affects the performance of a neural network when compared to the resolution of the hidden layers ("internal resolution").
Information-Bottleneck Approach to Salient Region Discovery
We propose a new method for learning image attention masks in a semi-supervised setting based on the Information Bottleneck principle.
Adversarial Attacks in Sound Event Classification
In addition, we show that the adversarial attacks are very effective across the different models.
Efficient On-line Computation of Visibility Graphs
The empirical evidence suggests the proposed method for computation of visibility graphs offers an on-line computation solution at no additional computation time cost.
Data Structures and Algorithms
Searching for MobileNetV3
We achieve new state of the art results for mobile classification, detection and segmentation.
Ranked #9 on
Dichotomous Image Segmentation
on DIS-TE1
K For The Price Of 1: Parameter Efficient Multi-task And Transfer Learning
We introduce a novel method that enables parameter-efficient transfer and multitask learning.
Visibility graphs for robust harmonic similarity measures between audio spectra
We present experiments demonstrating the utility of this distance measure for real and synthesised audio data.
Sound Audio and Speech Processing
K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning
We introduce a novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks.
MnasNet: Platform-Aware Neural Architecture Search for Mobile
In this paper, we propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency.
Ranked #885 on
Image Classification
on ImageNet
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
This work proposes an algorithm, called NetAdapt, that automatically adapts a pre-trained deep neural network to a mobile platform given a resource budget.
MobileNetV2: Inverted Residuals and Linear Bottlenecks
In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes.
Ranked #7 on
Retinal OCT Disease Classification
on OCT2017
CycleGAN, a Master of Steganography
CycleGAN (Zhu et al. 2017) is one recent successful approach to learn a transformation between two image distributions.
A Tutorial on Deep Learning for Music Information Retrieval
Following their success in Computer Vision and other areas, deep learning techniques have recently become widely adopted in Music Information Retrieval (MIR) research.
A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging
In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks.
The Effects of Noisy Labels on Deep Convolutional Neural Networks for Music Tagging
The results highlight several important aspects of music tagging and neural networks.
Transfer learning for music classification and regression tasks
In this paper, we present a transfer learning approach for music classification and regression tasks.
The Power of Sparsity in Convolutional Neural Networks
Deep convolutional networks are well-known for their high computational and memory demands.
Convolutional Recurrent Neural Networks for Music Classification
We introduce a convolutional recurrent neural network (CRNN) for music tagging.
Towards Music Captioning: Generating Music Playlist Descriptions
Descriptions are often provided along with recommendations to help users' discovery.
Explaining Deep Convolutional Neural Networks on Music Classification
Deep convolutional neural networks (CNNs) have been actively adopted in the field of music information retrieval, e. g. genre classification, mood detection, and chord recognition.
Inverting face embeddings with convolutional neural networks
Deep neural networks have dramatically advanced the state of the art for many areas of machine learning.
Towards Playlist Generation Algorithms Using RNNs Trained on Within-Track Transitions
We introduce a novel playlist generation algorithm that focuses on the quality of transitions using a recurrent neural network (RNN).
Automatic tagging using deep convolutional neural networks
We present a content-based automatic music tagging algorithm using fully convolutional neural networks (FCNs).
Text-based LSTM networks for Automatic Music Composition
In this paper, we introduce new methods and discuss results of text-based LSTM (Long Short-Term Memory) networks for automatic music composition.
