One of the greatest goals of AI is building an artificial continuous learning agent which can construct a sophisticated understanding about the external world from its own experience through the adaptive, goal-oriented and incremental development of ever more complex skills and knowledge. Yet, Continuous/Lifelong Learning (CL) from high-dimensional streaming data is a challenging research problem far from being solved. In fact, fully retraining deep prediction models each time a new piece of data becomes available is infeasible, due to computational and storage issues, while naïve continuous learning strategies have been shown to suffer from catastrophic forgetting. This talk will cover some of the most common end-to-end continuous learning strategies for gradient-based architectures and the recently proposed AR-1 strategy, which can outperform other state-of-the-art regularization and architectural approaches on the CORe50 benchmark.
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or image captioning.
Slides by Miriam Bellver from the Computer Vision Reading Group at the Universitat Politecnica de Catalunya about the paper:
Lu, Yongxi, Tara Javidi, and Svetlana Lazebnik. "Adaptive Object Detection Using Adjacency and Zoom Prediction." CVPR 2016
Abstract:
State-of-the-art object detection systems rely on an accurate set of region proposals. Several recent methods use a neural network architecture to hypothesize promising object locations. While these approaches are computationally efficient, they rely on fixed image regions as anchors for predictions. In this paper we propose to use a search strategy that adaptively directs computational resources to sub-regions likely to contain objects. Compared to methods based on fixed anchor locations, our approach naturally adapts to cases where object instances are sparse and small. Our approach is comparable in terms of accuracy to the state-of-the-art Faster R-CNN approach while using two orders of magnitude fewer anchors on average. Code is publicly available.
https://telecombcn-dl.github.io/2017-dlcv/
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or image captioning.
Ukrainian Catholic University
Faculty of Applied Sciences
Data Science Master Program
January 23rd
Abstract. Speaker classification is an essential task in the machine learning domain, with many practical applications in identification and natural language processing. This work concentrates on speaker classification as a subtask of general speaker diarization for real-world conversation scenarios. We research the domain of modern speech processing and present the original speaker classification approach based on the recent developments in convolutional neural networks. Our method uses a spectrogram as input to the CNN classifier model, allowing it to capture spatial information about voice frequencies distribution. Presented results show beyond human ability performance and give strong prospects for future development.
https://telecombcn-dl.github.io/2018-dlcv/
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or image captioning.
https://telecombcn-dl.github.io/2017-dlcv/
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or image captioning.
https://telecombcn-dl.github.io/2018-dlcv/
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or image captioning.
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or image captioning.
Slides by Miriam Bellver from the Computer Vision Reading Group at the Universitat Politecnica de Catalunya about the paper:
Lu, Yongxi, Tara Javidi, and Svetlana Lazebnik. "Adaptive Object Detection Using Adjacency and Zoom Prediction." CVPR 2016
Abstract:
State-of-the-art object detection systems rely on an accurate set of region proposals. Several recent methods use a neural network architecture to hypothesize promising object locations. While these approaches are computationally efficient, they rely on fixed image regions as anchors for predictions. In this paper we propose to use a search strategy that adaptively directs computational resources to sub-regions likely to contain objects. Compared to methods based on fixed anchor locations, our approach naturally adapts to cases where object instances are sparse and small. Our approach is comparable in terms of accuracy to the state-of-the-art Faster R-CNN approach while using two orders of magnitude fewer anchors on average. Code is publicly available.
https://telecombcn-dl.github.io/2017-dlcv/
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or image captioning.
Ukrainian Catholic University
Faculty of Applied Sciences
Data Science Master Program
January 23rd
Abstract. Speaker classification is an essential task in the machine learning domain, with many practical applications in identification and natural language processing. This work concentrates on speaker classification as a subtask of general speaker diarization for real-world conversation scenarios. We research the domain of modern speech processing and present the original speaker classification approach based on the recent developments in convolutional neural networks. Our method uses a spectrogram as input to the CNN classifier model, allowing it to capture spatial information about voice frequencies distribution. Presented results show beyond human ability performance and give strong prospects for future development.
https://telecombcn-dl.github.io/2018-dlcv/
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or image captioning.
https://telecombcn-dl.github.io/2017-dlcv/
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or image captioning.
https://telecombcn-dl.github.io/2018-dlcv/
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or image captioning.
Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...Vincenzo Lomonaco
Continual Learning (CL) is a fast emerging topic in AI concerning the ability to efficiently improve the performance of a deep model over time, dealing with a long (and possibly unlimited) sequence of data/tasks. In this workshop, after a brief introduction of the subject, we’ll analyze different Continual Learning strategies and assess them on common Vision benchmarks. We’ll conclude the workshop with a look at possible real world application of CL.
Continual/Lifelong Learning with Deep Architectures, Vincenzo LomonacoData Science Milan
Humans have the extraordinary ability to learn continually from experience. Not only can we apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning. One of the grand goals of AI is building an artificial continually learning agent that constructs a sophisticated understanding of the world from its own experience through the autonomous incremental development of ever more complex skills and knowledge.
"Continual Learning" (CL) is indeed a fast emerging topic in AI concerning the ability to efficiently improve the performance of a deep model over time, dealing with a long (and possibly unlimited) sequence of data/tasks. In this workshop, after a brief introduction of the topic, we’ll implement different Continual Learning strategies and assess them on common vision benchmarks. We’ll conclude the workshop with a look at possible real world applications of CL.
Vincenzo Lomonaco is a Deep Learning PhD student at the University of Bologna and founder of ContinualAI.org. He is also the PhD students representative at the Department of Computer Science of Engineering (DISI) and teaching assistant of the courses “Machine Learning” and “Computer Architectures” in the same department. Previously, he was a Machine Learning software engineer at IDL in-line Devices and a Master Student at the University of Bologna where he graduated cum laude in 2015 with the dissertation “Deep Learning for Computer Vision: a Comparison Between CNNs and HTMs on Object Recognition Tasks".
Artificial agents interacting in highly dynamic environments are required to continually acquire and fine-tune their knowledge overtime. In contrast to conventional deep neural networks that typically rely on a large batch of annotated training samples, lifelong learning systems must account for situations in which the number of tasks is not known a priori and the data samples become incrementally available over time. Despite recent advances in deep learning, lifelong machine learning has remained a long-standing challenge due to neural networks being prone to catastrophic forgetting, i.e., the learning of new tasks interferes with previously learned ones and leads to abrupt disruptions of performance. Recently proposed deep supervised and reinforcement learning models for addressing catastrophic forgetting suffer from flexibility, robustness, and scalability issues with respect to biological systems. In this tutorial, we will present and discuss well-established and emerging neural network approaches motivated by lifelong learning factors in biological systems such as neurosynaptic plasticity, complementary memory systems, multi-task transfer learning, and intrinsically motivated exploration.
Continual/Lifelong Learning with Deep ArchitecturesVincenzo Lomonaco
Humans have the extraordinary ability to learn continually from experience. Not only can we apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning. One of the grand goals of AI is building an artificial continually learning agent that constructs a sophisticated understanding of the world from its own experience through the autonomous incremental development of ever more complex skills and knowledge.
"Continual Learning" (CL) is indeed a fast emerging topic in AI concerning the ability to efficiently improve the performance of a deep model over time, dealing with a long (and possibly unlimited) sequence of data/tasks. In this workshop, after a brief introduction of the topic, we’ll implement different Continual Learning strategies and assess them on common vision benchmarks. We’ll conclude the workshop with a look at possible real world applications of CL.
CORe50: a New Dataset and Benchmark for Continuous Object Recognition PosterVincenzo Lomonaco
Continuous/Lifelong learning of high-dimensional data streams is a challenging research problem. In fact, fully retraining models each time new data become available is infeasible, due to computational and storage issues, while na\"ive incremental strategies have been shown to suffer from catastrophic forgetting. In the context of real-world object recognition applications (e.g., robotic vision), where continuous learning is crucial, very few datasets and benchmarks are available to evaluate and compare emerging techniques. In this work we propose a new dataset and benchmark CORe50, specifically designed for continuous object recognition, and introduce baseline approaches for different continuous learning scenarios.
Continual Reinforcement Learning in 3D Non-stationary EnvironmentsVincenzo Lomonaco
Dynamic and always-changing environments constitute an hard challenge for current reinforcement learning techniques. Artificial agents, nowadays, are often trained in very static and reproducible conditions in simulation, where the common assumption is that observations can be sampled i.i.d from the environment. However, tackling more complex problems and real-world settings this can be rarely considered the case, with environments often non-stationary and subject to unpredictable, frequent changes. In this talk we discuss about a new open benchmark for learning continually through reinforce in a complex 3D non-stationary object picking task based on VizDoom and subject to several environmental changes. We further propose a number of end-to-end, model-free continual reinforcement learning strategies showing competitive results even without any access to previously encountered environmental conditions or observations.
Object detection is a central problem in computer vision and underpins many applications from medical image analysis to autonomous driving. In this talk, we will review the basics of object detection from fundamental concepts to practical techniques. Then, we will dive into cutting-edge methods that use transformers to drastically simplify the object detection pipeline while maintaining predictive performance. Finally, we will show how to train these models at scale using Determined’s integrated deep learning platform and then serve the models using MLflow.
What you will learn:
Basics of object detection including main concepts and techniques
Main ideas from the DETR and Deformable DETR approaches to object detection
Overview of the core capabilities of Determined’s deep learning platform, with a focus on its support for effortless distributed training
How to serve models trained in Determined using MLflow
Recurrent Neural Networks (RNNs) represent the reference class of Deep Learning models for learning from sequential data. Despite the widespread success, a major downside of RNNs and commonly derived ‘gating’ variants (LSTM, GRU) is given by the high cost of the involved training algorithms. In this context, an increasingly popular alternative is the Reservoir Computing (RC) approach, which enables limiting the training algorithm to operate only on a restricted set of (output) parameters. RC is appealing for several reasons, including the amenability of being implemented in low-powerful edge devices, enabling adaptation and personalization in IoT and cyber-physical systems applications.
This webinar will introduce Reservoir Computing from scratch, covering all the fundamental design topics as well as good practices. It is targeted to both researchers and practitioners that are interested in setting up fastly-trained Deep Learning models for sequential data.
https://telecombcn-dl.github.io/2018-dlcv/
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or image captioning.
Representational Continuity for Unsupervised Continual LearningMLAI2
Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual learning (SCL) scenarios. Consequently, they are not scalable to real-world applications where the data distribution is often biased and unannotated. In this work, we focus on unsupervised continual learning (UCL), where we learn the feature representations on an unlabelled sequence of tasks and show that reliance on annotated data is not necessary for continual learning. We conduct a systematic study analyzing the learned feature representations and show that unsupervised visual representations are surprisingly more robust to catastrophic forgetting, consistently achieve better performance, and generalize better to out-of-distribution tasks than SCL. Furthermore, we find that UCL achieves a smoother loss landscape through qualitative analysis of the learned representations and learns meaningful feature representations. Additionally, we propose Lifelong Unsupervised Mixup (Lump), a simple yet effective technique that interpolates between the current task and previous tasks' instances to alleviate catastrophic forgetting for unsupervised representations.
The presentation is coverong the convolution neural network (CNN) design.
First,
the main building blocks of CNNs will be introduced. Then we systematically
investigate the impact of a range of recent advances in CNN architectures and
learning methods on the object categorization (ILSVRC) problem. In the
evaluation, the influence of the following choices of the architecture are
tested: non-linearity (ReLU, ELU, maxout, compatibility with batch
normalization), pooling variants (stochastic, max, average, mixed), network
width, classifier design (convolution, fully-connected, SPP), image
pre-processing, and of learning parameters: learning rate, batch size,
cleanliness of the data, etc.
Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning techniques, researchers in multiple communities are now striving to bridge videos with natural language in order to move beyond classification to interpretation, which should be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques.
The Deep Continual Learning community should move beyond studying forgetting in Class-Incremental Learning Scenarios! In this tutorial we gave at
#CoLLAs2023, me and Antonio Carta try to explain why and how! 👇
Do you agree?
Continual Learning with Deep Architectures - Tutorial ICML 2021Vincenzo Lomonaco
Humans have the extraordinary ability to learn continually from experience. Not only we can apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning. One of the grand goals of Artificial Intelligence (AI) is building an artificial “continual learning” agent that constructs a sophisticated understanding of the world from its own experience through the autonomous incremental development of ever more complex knowledge and skills (Parisi, 2019). However, despite early speculations and few pioneering works (Ring, 1998; Thrun, 1998; Carlson, 2010), very little research and effort has been devoted to address this vision. Current AI systems greatly suffer from the exposure to new data or environments which even slightly differ from the ones for which they have been trained for (Goodfellow, 2013). Moreover, the learning process is usually constrained on fixed datasets within narrow and isolated tasks which may hardly lead to the emergence of more complex and autonomous intelligent behaviors. In essence, continual learning and adaptation capabilities, while more than often thought as fundamental pillars of every intelligent agent, have been mostly left out of the main AI research focus.
In this tutorial, we propose to summarize the application of these ideas in light of the more recent advances in machine learning research and in the context of deep architectures for AI (Lomonaco, 2019). Starting from a motivation and a brief history, we link recent Continual Learning advances to previous research endeavours on related topics and we summarize the state-of-the-art in terms of major approaches, benchmarks and key results. In the second part of the tutorial we plan to cover more exploratory studies about Continual Learning with low supervised signals and the relationships with other paradigms such as Unsupervised, Semi-Supervised and Reinforcement Learning. We will also highlight the impact of recent Neuroscience discoveries in the design of original continual learning algorithms as well as their deployment in real-world applications. Finally, we will underline the notion of continual learning as a key technological enabler for Sustainable Machine Learning and its societal impact, as well as recap interesting research questions and directions worth addressing in the future.
Authors: Vincenzo Lomonaco, Irina Rish
Official Website: https://sites.google.com/view/cltutorial-icml2021
More Related Content
Similar to Continuous Learning with Deep Architectures
Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...Vincenzo Lomonaco
Continual Learning (CL) is a fast emerging topic in AI concerning the ability to efficiently improve the performance of a deep model over time, dealing with a long (and possibly unlimited) sequence of data/tasks. In this workshop, after a brief introduction of the subject, we’ll analyze different Continual Learning strategies and assess them on common Vision benchmarks. We’ll conclude the workshop with a look at possible real world application of CL.
Continual/Lifelong Learning with Deep Architectures, Vincenzo LomonacoData Science Milan
Humans have the extraordinary ability to learn continually from experience. Not only can we apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning. One of the grand goals of AI is building an artificial continually learning agent that constructs a sophisticated understanding of the world from its own experience through the autonomous incremental development of ever more complex skills and knowledge.
"Continual Learning" (CL) is indeed a fast emerging topic in AI concerning the ability to efficiently improve the performance of a deep model over time, dealing with a long (and possibly unlimited) sequence of data/tasks. In this workshop, after a brief introduction of the topic, we’ll implement different Continual Learning strategies and assess them on common vision benchmarks. We’ll conclude the workshop with a look at possible real world applications of CL.
Vincenzo Lomonaco is a Deep Learning PhD student at the University of Bologna and founder of ContinualAI.org. He is also the PhD students representative at the Department of Computer Science of Engineering (DISI) and teaching assistant of the courses “Machine Learning” and “Computer Architectures” in the same department. Previously, he was a Machine Learning software engineer at IDL in-line Devices and a Master Student at the University of Bologna where he graduated cum laude in 2015 with the dissertation “Deep Learning for Computer Vision: a Comparison Between CNNs and HTMs on Object Recognition Tasks".
Artificial agents interacting in highly dynamic environments are required to continually acquire and fine-tune their knowledge overtime. In contrast to conventional deep neural networks that typically rely on a large batch of annotated training samples, lifelong learning systems must account for situations in which the number of tasks is not known a priori and the data samples become incrementally available over time. Despite recent advances in deep learning, lifelong machine learning has remained a long-standing challenge due to neural networks being prone to catastrophic forgetting, i.e., the learning of new tasks interferes with previously learned ones and leads to abrupt disruptions of performance. Recently proposed deep supervised and reinforcement learning models for addressing catastrophic forgetting suffer from flexibility, robustness, and scalability issues with respect to biological systems. In this tutorial, we will present and discuss well-established and emerging neural network approaches motivated by lifelong learning factors in biological systems such as neurosynaptic plasticity, complementary memory systems, multi-task transfer learning, and intrinsically motivated exploration.
Continual/Lifelong Learning with Deep ArchitecturesVincenzo Lomonaco
Humans have the extraordinary ability to learn continually from experience. Not only can we apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning. One of the grand goals of AI is building an artificial continually learning agent that constructs a sophisticated understanding of the world from its own experience through the autonomous incremental development of ever more complex skills and knowledge.
"Continual Learning" (CL) is indeed a fast emerging topic in AI concerning the ability to efficiently improve the performance of a deep model over time, dealing with a long (and possibly unlimited) sequence of data/tasks. In this workshop, after a brief introduction of the topic, we’ll implement different Continual Learning strategies and assess them on common vision benchmarks. We’ll conclude the workshop with a look at possible real world applications of CL.
CORe50: a New Dataset and Benchmark for Continuous Object Recognition PosterVincenzo Lomonaco
Continuous/Lifelong learning of high-dimensional data streams is a challenging research problem. In fact, fully retraining models each time new data become available is infeasible, due to computational and storage issues, while na\"ive incremental strategies have been shown to suffer from catastrophic forgetting. In the context of real-world object recognition applications (e.g., robotic vision), where continuous learning is crucial, very few datasets and benchmarks are available to evaluate and compare emerging techniques. In this work we propose a new dataset and benchmark CORe50, specifically designed for continuous object recognition, and introduce baseline approaches for different continuous learning scenarios.
Continual Reinforcement Learning in 3D Non-stationary EnvironmentsVincenzo Lomonaco
Dynamic and always-changing environments constitute an hard challenge for current reinforcement learning techniques. Artificial agents, nowadays, are often trained in very static and reproducible conditions in simulation, where the common assumption is that observations can be sampled i.i.d from the environment. However, tackling more complex problems and real-world settings this can be rarely considered the case, with environments often non-stationary and subject to unpredictable, frequent changes. In this talk we discuss about a new open benchmark for learning continually through reinforce in a complex 3D non-stationary object picking task based on VizDoom and subject to several environmental changes. We further propose a number of end-to-end, model-free continual reinforcement learning strategies showing competitive results even without any access to previously encountered environmental conditions or observations.
Object detection is a central problem in computer vision and underpins many applications from medical image analysis to autonomous driving. In this talk, we will review the basics of object detection from fundamental concepts to practical techniques. Then, we will dive into cutting-edge methods that use transformers to drastically simplify the object detection pipeline while maintaining predictive performance. Finally, we will show how to train these models at scale using Determined’s integrated deep learning platform and then serve the models using MLflow.
What you will learn:
Basics of object detection including main concepts and techniques
Main ideas from the DETR and Deformable DETR approaches to object detection
Overview of the core capabilities of Determined’s deep learning platform, with a focus on its support for effortless distributed training
How to serve models trained in Determined using MLflow
Recurrent Neural Networks (RNNs) represent the reference class of Deep Learning models for learning from sequential data. Despite the widespread success, a major downside of RNNs and commonly derived ‘gating’ variants (LSTM, GRU) is given by the high cost of the involved training algorithms. In this context, an increasingly popular alternative is the Reservoir Computing (RC) approach, which enables limiting the training algorithm to operate only on a restricted set of (output) parameters. RC is appealing for several reasons, including the amenability of being implemented in low-powerful edge devices, enabling adaptation and personalization in IoT and cyber-physical systems applications.
This webinar will introduce Reservoir Computing from scratch, covering all the fundamental design topics as well as good practices. It is targeted to both researchers and practitioners that are interested in setting up fastly-trained Deep Learning models for sequential data.
https://telecombcn-dl.github.io/2018-dlcv/
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or image captioning.
Representational Continuity for Unsupervised Continual LearningMLAI2
Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual learning (SCL) scenarios. Consequently, they are not scalable to real-world applications where the data distribution is often biased and unannotated. In this work, we focus on unsupervised continual learning (UCL), where we learn the feature representations on an unlabelled sequence of tasks and show that reliance on annotated data is not necessary for continual learning. We conduct a systematic study analyzing the learned feature representations and show that unsupervised visual representations are surprisingly more robust to catastrophic forgetting, consistently achieve better performance, and generalize better to out-of-distribution tasks than SCL. Furthermore, we find that UCL achieves a smoother loss landscape through qualitative analysis of the learned representations and learns meaningful feature representations. Additionally, we propose Lifelong Unsupervised Mixup (Lump), a simple yet effective technique that interpolates between the current task and previous tasks' instances to alleviate catastrophic forgetting for unsupervised representations.
The presentation is coverong the convolution neural network (CNN) design.
First,
the main building blocks of CNNs will be introduced. Then we systematically
investigate the impact of a range of recent advances in CNN architectures and
learning methods on the object categorization (ILSVRC) problem. In the
evaluation, the influence of the following choices of the architecture are
tested: non-linearity (ReLU, ELU, maxout, compatibility with batch
normalization), pooling variants (stochastic, max, average, mixed), network
width, classifier design (convolution, fully-connected, SPP), image
pre-processing, and of learning parameters: learning rate, batch size,
cleanliness of the data, etc.
Video has become ubiquitous on the Internet, TV, as well as personal devices. Recognition of video content has been a fundamental challenge in computer vision for decades, where previous research predominantly focused on recognizing videos using a predefined yet limited vocabulary. Thanks to the recent development of deep learning techniques, researchers in multiple communities are now striving to bridge videos with natural language in order to move beyond classification to interpretation, which should be regarded as the ultimate goal of video understanding. We will present recent advances in exploring the synergy of video understanding and language processing techniques.
The Deep Continual Learning community should move beyond studying forgetting in Class-Incremental Learning Scenarios! In this tutorial we gave at
#CoLLAs2023, me and Antonio Carta try to explain why and how! 👇
Do you agree?
Continual Learning with Deep Architectures - Tutorial ICML 2021Vincenzo Lomonaco
Humans have the extraordinary ability to learn continually from experience. Not only we can apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning. One of the grand goals of Artificial Intelligence (AI) is building an artificial “continual learning” agent that constructs a sophisticated understanding of the world from its own experience through the autonomous incremental development of ever more complex knowledge and skills (Parisi, 2019). However, despite early speculations and few pioneering works (Ring, 1998; Thrun, 1998; Carlson, 2010), very little research and effort has been devoted to address this vision. Current AI systems greatly suffer from the exposure to new data or environments which even slightly differ from the ones for which they have been trained for (Goodfellow, 2013). Moreover, the learning process is usually constrained on fixed datasets within narrow and isolated tasks which may hardly lead to the emergence of more complex and autonomous intelligent behaviors. In essence, continual learning and adaptation capabilities, while more than often thought as fundamental pillars of every intelligent agent, have been mostly left out of the main AI research focus.
In this tutorial, we propose to summarize the application of these ideas in light of the more recent advances in machine learning research and in the context of deep architectures for AI (Lomonaco, 2019). Starting from a motivation and a brief history, we link recent Continual Learning advances to previous research endeavours on related topics and we summarize the state-of-the-art in terms of major approaches, benchmarks and key results. In the second part of the tutorial we plan to cover more exploratory studies about Continual Learning with low supervised signals and the relationships with other paradigms such as Unsupervised, Semi-Supervised and Reinforcement Learning. We will also highlight the impact of recent Neuroscience discoveries in the design of original continual learning algorithms as well as their deployment in real-world applications. Finally, we will underline the notion of continual learning as a key technological enabler for Sustainable Machine Learning and its societal impact, as well as recap interesting research questions and directions worth addressing in the future.
Authors: Vincenzo Lomonaco, Irina Rish
Official Website: https://sites.google.com/view/cltutorial-icml2021
Humans have the extraordinary ability to learn continually from experience. Not only we can apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning, constantly and efficiently updating our biased understanding of the external world. On the contrary, current AI systems are usually trained offline on huge datasets and later deployed with frozen learning capabilities as they have been shown to suffer from catastrophic forgetting if trained continuously on changing data distributions. A common, practical solution to the problem is to re-train the underlying prediction model from scratch and re-deploy it as a new batch of data becomes available. However, this naive approach is incredibly wasteful in terms of memory and computation other than impossible to sustain over longer timescales and frequent updates. In this talk, we will introduce an efficient continual learning strategy, which can reduce the amount of computation and memory overhead of more than 45% w.r.t. the standard re-train & re-deploy approach, further exploring its real-world application in the context of continual object recognition, running on the edge on highly-constrained hardware platforms such as widely adopted smartphones devices.
Continual Learning: Another Step Towards Truly Intelligent MachinesVincenzo Lomonaco
Humans have the extraordinary ability to learn continually from experience. Not only we can apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning. One of the grand goals of Artificial Intelligence (AI) is building an artificial continual learning agent that constructs a sophisticated understanding of the world from its own experience through the autonomous incremental development of ever more complex knowledge and skills. However, current AI systems greatly suffer from the exposure to new data or environments which even slightly differ from the ones for which they have been trained for. Moreover, the learning process is usually constrained on fixed datasets within narrow and isolated tasks which may hardly lead to the emergence of more complex and autonomous intelligent behaviors. In essence, continual learning and adaptation capabilities, while more than often thought as fundamental pillars of every intelligent agent, have been mostly left out of the main AI research focus. In this talk, we explore the application of these ideas in the context of Vision with a focus on (deep) continual learning strategies for object recognition running at the edge on highly-constrained hardware devices.
Humans have the extraordinary ability to learn continually from experience. Not only we can apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning. One of the grand goals of Artificial Intelligence (AI) is building an artificial continual learning agent that constructs a sophisticated understanding of the world from its own experience through the autonomous incremental development of ever more complex knowledge and skills. However, current AI systems greatly suffer from the exposure to new data or environments which even slightly differ from the ones for which they have been trained for. Moreover, the learning process is usually constrained on fixed datasets within narrow and isolated tasks which may hardly lead to the emergence of more complex and autonomous intelligent behaviors. In essence, continual learning and adaptation capabilities, while more than often thought as fundamental pillars of every intelligent agent, have been mostly left out of the main AI research focus. In this talk, we explore the application of these ideas in the context of Robotics with a focus on (deep) continual learning strategies for object recognition running at the edge on highly-constrained hardware devices.
Don't forget, there is more than forgetting: new metrics for Continual Learni...Vincenzo Lomonaco
Continual learning consists of algorithms that learn from a stream of data/tasks continuously and adaptively thought time, enabling the incremental development of ever more complex knowledge and skills. The lack of consensus in evaluating continual learning algorithms and the almost exclusive focus on forgetting motivate us to propose a more comprehensive set of implementation independent metrics accounting for several factors we believe have practical implications worth considering in the deployment of real AI systems that learn continually: accuracy or performance over time, backward and forward knowledge transfer, memory overhead as well as computational efficiency. Drawing inspiration from the standard Multi-Attribute Value Theory (MAVT) we further propose to fuse these metrics into a single score for ranking purposes and we evaluate our proposal with five continual learning strategies on the iCIFAR-100 continual learning benchmark.
Open-Source Frameworks for Deep Learning: an OverviewVincenzo Lomonaco
The rise of deep learning over the last decade has led to profound changes in the landscape of the machine learning software stack both for research and production. In this talk we will provide a comprehensive overview of the open-source deep learning frameworks landscape with both a theoretical and hands-on approach. After a brief introduction and historical contextualization, we will highlight common features and distinctions of their recent developments. Finally, we will take at deeper look into three of the most used deep learning frameworks today: Caffe, Tensorflow, PyTorch; with practical examples and considerations worth reckoning in the choice of such libraries.
CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...Vincenzo Lomonaco
Continuous/Lifelong learning of high-dimensional data streams is a challenging research problem. In fact, fully retraining models each time new data become available is infeasible, due to computational and storage issues, while na\"ive incremental strategies have been shown to suffer from catastrophic forgetting. In the context of real-world object recognition applications (e.g., robotic vision), where continuous learning is crucial, very few datasets and benchmarks are available to evaluate and compare emerging techniques. In this work we propose a new dataset and benchmark CORe50, specifically designed for continuous object recognition, and introduce baseline approaches for different continuous learning scenarios.
Continuous Unsupervised Training of Deep ArchitecturesVincenzo Lomonaco
A number of successful Computer Vision applications have been recently proposed based on Convolutional Networks. However, in most of the cases the system is fully supervised, the training set is fixed and the task completely defined a priori. Even though Transfer Learning approaches proved to be very useful to adapt heavily pre-trained models to ever-changing scenarios, the incremental learning and adaptation capabilities of existing models is still limited and catastrophic forgetting very difficult to control. In this talk we will discuss our experience in the design of deep architectures and algorithms capable of learning objects incrementally both in a supervised and unsupervised way. Finally we will introduce a new dataset and benchmark (CORe50) that we specifically collected to focus on continuous object recognition for Robotic Vision.
Comparing Incremental Learning Strategies for Convolutional Neural NetworksVincenzo Lomonaco
In the last decade, Convolutional Neural Networks (CNNs) have shown to perform incredibly well in many computer vision tasks such as object recognition and object detection, being able to extract meaningful high-level invariant features. However, partly because of their complex training and tricky hyper-parameters tuning, CNNs have been scarcely studied in the context of incremental learning where data are available in consecutive batches and retraining the model from scratch is unfeasible. In this work we compare different incremental learning strategies for CNN based architectures, targeting real-word applications.
If you are interested in this work please cite:
Lomonaco, V., & Maltoni, D. (2016, September). Comparing Incremental Learning Strategies for Convolutional Neural Networks. In IAPR Workshop on Artificial Neural Networks in Pattern Recognition (pp. 175-184). Springer International Publishing.
For further information visit my website: http://www.vincenzolomonaco.com/
Deep Learning for Computer Vision: A comparision between Convolutional Neural...Vincenzo Lomonaco
In recent years, Deep Learning techniques have shown to perform well on a large variety of problems both in Computer Vision and Natural Language Processing, reaching and often surpassing the state of the art on many tasks. The rise of deep learning is also revolutionizing the entire field of Machine Learning and Pattern Recognition pushing forward the concepts of automatic feature extraction and unsupervised learning in general.
However, despite the strong success both in science and business, deep learning has its own limitations. It is often questioned if such techniques are only some kind of brute-force statistical approaches and if they can only work in the context of High Performance Computing with tons of data. Another important question is whether they are really biologically inspired, as claimed in certain cases, and if they can scale well in terms of “intelligence”.
The dissertation is focused on trying to answer these key questions in the context of Computer Vision and, in particular, Object Recognition, a task that has been heavily revolutionized by recent advances in the field. Practically speaking, these answers are based on an exhaustive comparison between two, very different, deep learning techniques on the aforementioned task: Convolutional Neural Network (CNN) and Hierarchical Temporal memory (HTM). They stand for two different approaches and points of view within the big hat of deep learning and are the best choices to understand and point out strengths and weaknesses of each of them.
CNN is considered one of the most classic and powerful supervised methods used today in machine learning and pattern recognition, especially in object recognition. CNNs are well received and accepted by the scientific community and are already deployed in large corporation like Google and Facebook for solving face recognition and image auto-tagging problems.
HTM, on the other hand, is known as a new emerging paradigm and a new meanly-unsupervised method, that is more biologically inspired. It tries to gain more insights from the computational neuroscience community in order to incorporate concepts like time, context and attention during the learning process which are typical of the human brain.
In the end, the thesis is supposed to prove that in certain cases, with a lower quantity of data, HTM can outperform CNN.
Deep Learning for Computer Vision: A comparision between Convolutional Neural...Vincenzo Lomonaco
In recent years, Deep Learning techniques have shown to perform well on a large variety of problems both in Computer Vision and Natural Language Processing, reaching and often surpassing the state of the art on many tasks. The rise of deep learning is also revolutionizing the entire field of Machine Learning and Pattern Recognition pushing forward the concepts of automatic feature extraction and unsupervised learning in general.
However, despite the strong success both in science and business, deep learning has its own limitations. It is often questioned if such techniques are only some kind of brute-force statistical approaches and if they can only work in the context of High Performance Computing with tons of data. Another important question is whether they are really biologically inspired, as claimed in certain cases, and if they can scale well in terms of “intelligence”.
The dissertation is focused on trying to answer these key questions in the context of Computer Vision and, in particular, Object Recognition, a task that has been heavily revolutionized by recent advances in the field. Practically speaking, these answers are based on an exhaustive comparison between two, very different, deep learning techniques on the aforementioned task: Convolutional Neural Network (CNN) and Hierarchical Temporal memory (HTM). They stand for two different approaches and points of view within the big hat of deep learning and are the best choices to understand and point out strengths and weaknesses of each of them.
CNN is considered one of the most classic and powerful supervised methods used today in machine learning and pattern recognition, especially in object recognition. CNNs are well received and accepted by the scientific community and are already deployed in large corporation like Google and Facebook for solving face recognition and image auto-tagging problems.
HTM, on the other hand, is known as a new emerging paradigm and a new meanly-unsupervised method, that is more biologically inspired. It tries to gain more insights from the computational neuroscience community in order to incorporate concepts like time, context and attention during the learning process which are typical of the human brain.
In the end, the thesis is supposed to prove that in certain cases, with a lower quantity of data, HTM can outperform CNN.
In this work we started to develop a novel framework for statically detecting deadlocks in a concurrent Java environment with asynchronous method calls and cooperative scheduling of method activations. Since this language features recursion and dynamic resource creation, dead-
lock detection is extremely complex and state-of-the-art solutions either give imprecise answers or do not scale. The basic component of the framework is a front-end inference algorithm that ex-
tracts abstract behavioral descriptions of methods, called contracts, which retain resource dependency information. This component is integrated with a back-end that analyze contracts and derive deadlock information computing a fixpoint semantics.
Deep Learning libraries and first experiments with TheanoVincenzo Lomonaco
In recent years, neural networks and deep learning techniques have shown to perform well on many
problems in image recognition, speech recognition, natural language processing and many other tasks.
As a result, a large number of libraries, toolkits and frameworks came out in different languages and
with different purposes. In this report, firstly we take a look at these projects and secondly we choose the
framework that best suits our needs: Theano. Eventually, we implement a simple convolutional neural net
using this framework to test both its ease-of-use and efficiency.
Word2vec on the italian language: first experimentsVincenzo Lomonaco
Word2vec model and application by Mikolov et al. have attracted a great amount of attention in recent years. The vector representations of words learned by word2vec models have been proven to be able to carry semantic meanings and are useful in various NLP tasks. In this work I try to reproduce the previously obtained results for the English language and to explore the possibility of doing the same for the Italian language.
Opendatabay - Open Data Marketplace.pptxOpendatabay
Opendatabay.com unlocks the power of data for everyone. Open Data Marketplace fosters a collaborative hub for data enthusiasts to explore, share, and contribute to a vast collection of datasets.
First ever open hub for data enthusiasts to collaborate and innovate. A platform to explore, share, and contribute to a vast collection of datasets. Through robust quality control and innovative technologies like blockchain verification, opendatabay ensures the authenticity and reliability of datasets, empowering users to make data-driven decisions with confidence. Leverage cutting-edge AI technologies to enhance the data exploration, analysis, and discovery experience.
From intelligent search and recommendations to automated data productisation and quotation, Opendatabay AI-driven features streamline the data workflow. Finding the data you need shouldn't be a complex. Opendatabay simplifies the data acquisition process with an intuitive interface and robust search tools. Effortlessly explore, discover, and access the data you need, allowing you to focus on extracting valuable insights. Opendatabay breaks new ground with a dedicated, AI-generated, synthetic datasets.
Leverage these privacy-preserving datasets for training and testing AI models without compromising sensitive information. Opendatabay prioritizes transparency by providing detailed metadata, provenance information, and usage guidelines for each dataset, ensuring users have a comprehensive understanding of the data they're working with. By leveraging a powerful combination of distributed ledger technology and rigorous third-party audits Opendatabay ensures the authenticity and reliability of every dataset. Security is at the core of Opendatabay. Marketplace implements stringent security measures, including encryption, access controls, and regular vulnerability assessments, to safeguard your data and protect your privacy.
Chatty Kathy - UNC Bootcamp Final Project Presentation - Final Version - 5.23...John Andrews
SlideShare Description for "Chatty Kathy - UNC Bootcamp Final Project Presentation"
Title: Chatty Kathy: Enhancing Physical Activity Among Older Adults
Description:
Discover how Chatty Kathy, an innovative project developed at the UNC Bootcamp, aims to tackle the challenge of low physical activity among older adults. Our AI-driven solution uses peer interaction to boost and sustain exercise levels, significantly improving health outcomes. This presentation covers our problem statement, the rationale behind Chatty Kathy, synthetic data and persona creation, model performance metrics, a visual demonstration of the project, and potential future developments. Join us for an insightful Q&A session to explore the potential of this groundbreaking project.
Project Team: Jay Requarth, Jana Avery, John Andrews, Dr. Dick Davis II, Nee Buntoum, Nam Yeongjin & Mat Nicholas
7. • Higher and realistic time-scale where data (and tasks)
become available only during time
• No access to previously encountered data.
• Constant computational and memory resources.
• Incremental development of ever more complex
knowledge and skills.
8.
9. Dataset, Benchmark, code and additional
information freely available at:
vlomonaco.github.io/core50
LomonacoV. and Maltoni D. CORe50: a New Dataset and Benchmark for ContinuousObject Recognition.CoRL2017.
19. Combining Architectural and Regularization
approaches
LomonacoV. and Maltoni D. Continuous Learning in Single-Incremental-TaskScenarios.To be published.
24. 𝑊𝑡𝑊𝑏...
𝐿0, … , 𝐿 𝑛−1 𝐿 𝑛
• Computational efficient
(independent from the
number of training
batches)
• Just one Ω 𝑘(running sum
+ max clip)
• CWR with zero-init
• CWR with mean-shift
AR-1 (Aerojet Rocketdyne) name of the booster under development in competition with the blue origin BE-4 to replace Russuan RD-180. Falcon 9 has booster B1029. united lunch alliance atals v