Multimodal learning

Last updated

Multimodal learning, in the context of machine learning, is a type of deep learning using a combination of various modalities of data, often arising in real-world applications. An example of multi-modal data is data that combines text (typically represented as feature vector) with imaging data consisting of pixel intensities and annotation tags. As these modalities have fundamentally different statistical properties, combining them is non-trivial, which is why specialized modelling strategies and algorithms are required. The model is then trained to able to understand and work with multiple forms of data.

Contents

Motivation

Many models and algorithms have been implemented to retrieve and classify certain types of data, e.g. image or text (where humans who interact with machines can extract images in the form of pictures and texts that could be any message etc.). However, data usually come with different modalities (it is the degree to which a system's components may be separated or combined) which carry different information. For example, it is very common to caption an image to convey the information not presented in the image itself. Similarly, sometimes it is more straightforward to use an image to describe the information which may not be obvious from texts. As a result, if different words appear in similar images, then these words likely describe the same thing. Conversely, if a word is used to describe seemingly dissimilar images, then these images may represent the same object. Thus, in cases dealing with multi-modal data, it is important to use a model which is able to jointly represent the information such that the model can capture the correlation structure between different modalities. Moreover, it should also be able to recover missing modalities given observed ones (e.g. predicting possible image object according to text description). The Multimodal Deep Boltzmann Machine model satisfies the above purposes.

Multimodal transformers

This section is an excerpt from Transformer (deep learning architecture) § Multimodality.[ edit ]

Transformers can also be used/adapted for modalities (input or output) beyond just text, usually by finding a way to "tokenize" the modality.

Vision transformers [1] adapt the transformer to computer vision by breaking down input images as a series of patches, turning them into vectors, and treating them like tokens in a standard transformer.

Conformer [2] and later Whisper [3] follow the same pattern for speech recognition, first turning the speech signal into a spectrogram, which is then treated like an image, i.e. broken down into a series of patches, turned into vectors and treated like tokens in a standard transformer.

Perceivers by Andrew Jaegle et al. (2021) [4] [5] can learn from large amounts of heterogeneous data.

Regarding image outputs, Peebles et al introduced a diffusion transformer (DiT) which facilitates use of the transformer architecture for diffusion-based image production. [6] Also, Google released a transformer-centric image generator called "Muse" based on parallel decoding and masked generative transformer technology. [7] (Transformers played a less-central role with prior image-producing technologies, [8] albeit still a significant one. [9] )

Multimodal large language models

This section is an excerpt from Large language model § Multimodality.[ edit ]

Multimodality means "having several modalities", and a "modality" refers to a type of input or output, such as video, image, audio, text, proprioception, etc. [10] There have been many AI models trained specifically to ingest one modality and output another modality, such as AlexNet for image to label, [11] visual question answering for image-text to text, [12] and speech recognition for speech to text.

A common method to create multimodal models out of an LLM is to "tokenize" the output of a trained encoder. Concretely, one can construct a LLM that can understand images as follows: take a trained LLM, and take a trained image encoder . Make a small multilayered perceptron , so that for any image , the post-processed vector has the same dimensions as an encoded token. That is an "image token". Then, one can interleave text tokens and image tokens. The compound model is then fine-tuned on an image-text dataset. This basic construction can be applied with more sophistication to improve the model. The image encoder may be frozen to improve stability. [13]

Flamingo demonstrated the effectiveness of the tokenization method, finetuning a pair of pretrained language model and image encoder to perform better on visual question answering than models trained from scratch. [14] Google PaLM model was fine-tuned into a multimodal model PaLM-E using the tokenization method, and applied to robotic control. [15] LLaMA models have also been turned multimodal using the tokenization method, to allow image inputs, [16] and video inputs. [17]

GPT-4 can use both text and image as inputs [18] (although the vision component wasn't released to the public until GPT-4V [19] ); Google DeepMind's Gemini is also multimodal. [20]

Multimodal deep Boltzmann machines

A Boltzmann machine is a type of stochastic neural network invented by Geoffrey Hinton and Terry Sejnowski in 1985. Boltzmann machines can be seen as the stochastic, generative counterpart of Hopfield nets. They are named after the Boltzmann distribution in statistical mechanics. The units in Boltzmann machines are divided into two groups: visible units and hidden units. Each unit is like a neuron with a binary output that represents whether it's activated or not. [21] General Boltzmann machines allow connection between any units. However, learning is impractical using general Boltzmann Machines because the computational time is exponential to the size of the machine[ citation needed ]. A more efficient architecture is called restricted Boltzmann machine where connection is only allowed between hidden unit and visible unit, which is described in the next section.

Multimodal deep Boltzmann machines can process and learn from different types of information, such as images and text, simultaneously. This can notably be done by having a separate deep Boltzmann machine for each modality, for example one for images and one for text, joined at an additional top hidden layer. [22]

Application

Multimodal deep Boltzmann machines are successfully used in classification and missing data retrieval. The classification accuracy of multimodal deep Boltzmann machine outperforms support vector machines, latent Dirichlet allocation and deep belief network, when models are tested on data with both image-text modalities or with single modality.[ citation needed ] Multimodal deep Boltzmann machines are also able to predict missing modalities given the observed ones with reasonably good precision.[ citation needed ] Self Supervised Learning brings a more interesting and powerful model for multimodality. OpenAI developed CLIP and DALL-E models that revolutionized multimodality.

Multimodal deep learning is used for cancer screening – at least one system under development integrates such different types of data. [23] [24]

See also

Related Research Articles

Multimodal interaction provides the user with multiple modes of interacting with a system. A multimodal interface provides several distinct tools for input and output of data.

<span class="mw-page-title-main">Feature learning</span> Set of learning techniques in machine learning

In machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task.

Neural machine translation (NMT) is an approach to machine translation that uses an artificial neural network to predict the likelihood of a sequence of words, typically modeling entire sentences in a single integrated model.

<span class="mw-page-title-main">Transformer (deep learning architecture)</span> Machine learning algorithm used for natural-language processing

A transformer is a deep learning architecture developed by Google and based on the multi-head attention mechanism, proposed in a 2017 paper "Attention Is All You Need". It has no recurrent units, and thus requires less training time than previous recurrent neural architectures, such as long short-term memory (LSTM), and its later variation has been prevalently adopted for training large language models (LLM) on large (language) datasets, such as the Wikipedia corpus and Common Crawl. Text is converted to numerical representations called tokens, and each token is converted into a vector via looking up from a word embedding table. At each layer, each token is then contextualized within the scope of the context window with other (unmasked) tokens via a parallel multi-head attention mechanism allowing the signal for key tokens to be amplified and less important tokens to be diminished. The transformer paper, published in 2017, is based on the softmax-based attention mechanism proposed by Bahdanau et. al. in 2014 for machine translation, and the Fast Weight Controller, similar to a transformer, proposed in 1992.

Bidirectional Encoder Representations from Transformers (BERT) is a language model based on the transformer architecture, notable for its dramatic improvement over previous state of the art models. It was introduced in October 2018 by researchers at Google. A 2020 literature survey concluded that "in a little over a year, BERT has become a ubiquitous baseline in Natural Language Processing (NLP) experiments counting over 150 research publications analyzing and improving the model."

Generative Pre-trained Transformer 3 (GPT-3) is a large language model released by OpenAI in 2020. Like its predecessor, GPT-2, it is a decoder-only transformer model of deep neural network, which supersedes recurrence and convolution-based architectures with a technique known as "attention". This attention mechanism allows the model to selectively focus on segments of input text it predicts to be most relevant. It uses a 2048-tokens-long context, float16 (16-bit) precision, and a hitherto-unprecedented 175 billion parameters, requiring 350GB of storage space as each parameter takes 2 bytes of space, and has demonstrated strong "zero-shot" and "few-shot" learning abilities on many tasks.

Machine learning-based attention is a mechanism which intuitively mimics cognitive attention. It calculates "soft" weights for each word, more precisely for its embedding, in the context window. These weights can be computed either in parallel or sequentially. "Soft" weights can change during each runtime, in contrast to "hard" weights, which are (pre-)trained and fine-tuned and remain frozen afterwards.

<span class="mw-page-title-main">DALL-E</span> Image-generating deep-learning model

DALL·E, DALL·E 2, and DALL·E 3 are text-to-image models developed by OpenAI using deep learning methodologies to generate digital images from natural language descriptions, called "prompts."

Self-supervised learning (SSL) is a paradigm in machine learning where a model is trained on a task using the data itself to generate supervisory signals, rather than relying on external labels provided by humans. In the context of neural networks, self-supervised learning aims to leverage inherent structures or relationships within the input data to create meaningful training signals. SSL tasks are designed so that solving it requires capturing essential features or relationships in the data. The input data is typically augmented or transformed in a way that creates pairs of related samples. One sample serves as the input, and the other is used to formulate the supervisory signal. This augmentation can involve introducing noise, cropping, rotation, or other transformations. Self-supervised learning more closely imitates the way humans learn to classify objects.

Wu Dao is a multimodal artificial intelligence developed by the Beijing Academy of Artificial Intelligence (BAAI). Wu Dao 1.0 was first announced on January 11, 2021; an improved version, Wu Dao 2.0, was announced on May 31. It has been compared to GPT-3, and is built on a similar architecture; in comparison, GPT-3 has 175 billion parameters — variables and inputs within the machine learning model — while Wu Dao has 1.75 trillion parameters. Wu Dao was trained on 4.9 terabytes of images and texts, while GPT-3 was trained on 45 terabytes of text data. Yet, a growing body of work highlights the importance of increasing both data and parameters. The chairman of BAAI said that Wu Dao was an attempt to "create the biggest, most powerful AI model possible"; although direct comparisons between models based on parameter count do not directly correlate to quality. Wu Dao 2.0, was called "the biggest language A.I. system yet". It was interpreted by commenters as an attempt to "compete with the United States".. Notably, the type of architecture used for Wu Dao 2.0 is a mixture-of-experts (MoE) model, unlike GPT-3, which is a "dense" model: while MoE models require much less computational power to train than dense models with the same numbers of parameters, trillion-parameter MoE models have shown comparable performance to models that are hundreds of times smaller.

A vision transformer (ViT) is a transformer designed for computer vision. A ViT breaks down an input image into a series of patches, serialises each patch into a vector, and maps it to a smaller dimension with a single matrix multiplication. These vector embeddings are then processed by a transformer encoder as if they were token embeddings.

Perceiver is a transformer adapted to be able to process non-textual data, such as images, sounds and video, and spatial data. Transformers underlie other notable systems such as BERT and GPT-3, which preceded Perceiver. It adopts an asymmetric attention mechanism to distill inputs into a latent bottleneck, allowing it to learn from large amounts of heterogeneous data. Perceiver matches or outperforms specialized models on classification tasks.

Prompt engineering is the process of structuring text that can be interpreted and understood by a generative AI model. A prompt is natural language text describing the task that an AI should perform.

A foundation model is a machine learning model that is trained on broad data such that it can be applied across a wide range of use cases. Foundation models have transformed artificial intelligence (AI), powering prominent generative AI applications like ChatGPT. The Stanford Institute for Human-Centered Artificial Intelligence's Center for Research on Foundation Models created and popularized the term.

<span class="mw-page-title-main">Stable Diffusion</span> Image-generating machine learning model

Stable Diffusion is a deep learning, text-to-image model released in 2022 based on diffusion techniques. It is considered to be a part of the ongoing AI boom.

<span class="mw-page-title-main">Text-to-image model</span> Machine learning model

A text-to-image model is a machine learning model which takes an input natural language description and produces an image matching that description.

<span class="mw-page-title-main">Generative pre-trained transformer</span> Type of large language model

Generative pre-trained transformers (GPT) are a type of large language model (LLM) and a prominent framework for generative artificial intelligence. They are artificial neural networks that are used in natural language processing tasks. GPTs are based on the transformer architecture, pre-trained on large data sets of unlabelled text, and able to generate novel human-like content. As of 2023, most LLMs have these characteristics and are sometimes referred to broadly as GPTs.

A large language model (LLM) is a language model notable for its ability to achieve general-purpose language generation and other natural language processing tasks such as classification. LLMs acquire these abilities by learning statistical relationships from text documents during a computationally intensive self-supervised and semi-supervised training process. LLMs can be used for text generation, a form of generative AI, by taking an input text and repeatedly predicting the next token or word.

In machine learning, a neural scaling law is a scaling law relating parameters of a family of neural networks.

Mamba is a deep learning architecture focused on sequence modeling. It was developed by researchers from Carnegie Mellon University and Princeton University to address some limitations of transformer models, especially in processing long sequences, and it is based on the Structured State Space sequence (S4) model.

References

  1. ↑ Dosovitskiy, Alexey; Beyer, Lucas; Kolesnikov, Alexander; Weissenborn, Dirk; Zhai, Xiaohua; Unterthiner, Thomas; Dehghani, Mostafa; Minderer, Matthias; Heigold, Georg; Gelly, Sylvain; Uszkoreit, Jakob (2021-06-03). "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale". arXiv: 2010.11929 [cs.CV].
  2. ↑ Gulati, Anmol; Qin, James; Chiu, Chung-Cheng; Parmar, Niki; Zhang, Yu; Yu, Jiahui; Han, Wei; Wang, Shibo; Zhang, Zhengdong; Wu, Yonghui; Pang, Ruoming (2020). "Conformer: Convolution-augmented Transformer for Speech Recognition". arXiv: 2005.08100 [eess.AS].
  3. ↑ Radford, Alec; Kim, Jong Wook; Xu, Tao; Brockman, Greg; McLeavey, Christine; Sutskever, Ilya (2022). "Robust Speech Recognition via Large-Scale Weak Supervision". arXiv: 2212.04356 [eess.AS].
  4. ↑ Jaegle, Andrew; Gimeno, Felix; Brock, Andrew; Zisserman, Andrew; Vinyals, Oriol; Carreira, Joao (2021-06-22). "Perceiver: General Perception with Iterative Attention". arXiv: 2103.03206 [cs.CV].
  5. ↑ Jaegle, Andrew; Borgeaud, Sebastian; Alayrac, Jean-Baptiste; Doersch, Carl; Ionescu, Catalin; Ding, David; Koppula, Skanda; Zoran, Daniel; Brock, Andrew; Shelhamer, Evan; Hénaff, Olivier (2021-08-02). "Perceiver IO: A General Architecture for Structured Inputs & Outputs". arXiv: 2107.14795 [cs.LG].
  6. ↑ Peebles, William; Xie, Saining (March 2, 2023). "Scalable Diffusion Models with Transformers". arXiv: 2212.09748 [cs.CV].
  7. ↑ "Google AI Unveils Muse, a New Text-to-Image Transformer Model". InfoQ.
  8. ↑ "Using Diffusion Models to Create Superior NeRF Avatars". January 5, 2023.
  9. ↑ Islam, Arham (November 14, 2022). "How Do DALL·E 2, Stable Diffusion, and Midjourney Work?".
  10. ↑ Kiros, Ryan; Salakhutdinov, Ruslan; Zemel, Rich (2014-06-18). "Multimodal Neural Language Models". Proceedings of the 31st International Conference on Machine Learning. PMLR: 595–603.
  11. ↑ Krizhevsky, Alex; Sutskever, Ilya; Hinton, Geoffrey E (2012). "ImageNet Classification with Deep Convolutional Neural Networks". Advances in Neural Information Processing Systems. Curran Associates, Inc. 25.
  12. ↑ Antol, Stanislaw; Agrawal, Aishwarya; Lu, Jiasen; Mitchell, Margaret; Batra, Dhruv; Zitnick, C. Lawrence; Parikh, Devi (2015). "VQA: Visual Question Answering". ICCV: 2425–2433.
  13. ↑ Li, Junnan; Li, Dongxu; Savarese, Silvio; Hoi, Steven (2023-01-01). "BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models". arXiv: 2301.12597 [cs.CV].
  14. ↑ Alayrac, Jean-Baptiste; Donahue, Jeff; Luc, Pauline; Miech, Antoine; Barr, Iain; Hasson, Yana; Lenc, Karel; Mensch, Arthur; Millican, Katherine; Reynolds, Malcolm; Ring, Roman; Rutherford, Eliza; Cabi, Serkan; Han, Tengda; Gong, Zhitao (2022-12-06). "Flamingo: a Visual Language Model for Few-Shot Learning". Advances in Neural Information Processing Systems. 35: 23716–23736. arXiv: 2204.14198 .
  15. ↑ Driess, Danny; Xia, Fei; Sajjadi, Mehdi S. M.; Lynch, Corey; Chowdhery, Aakanksha; Ichter, Brian; Wahid, Ayzaan; Tompson, Jonathan; Vuong, Quan; Yu, Tianhe; Huang, Wenlong; Chebotar, Yevgen; Sermanet, Pierre; Duckworth, Daniel; Levine, Sergey (2023-03-01). "PaLM-E: An Embodied Multimodal Language Model". arXiv: 2303.03378 [cs.LG].
  16. ↑ Liu, Haotian; Li, Chunyuan; Wu, Qingyang; Lee, Yong Jae (2023-04-01). "Visual Instruction Tuning". arXiv: 2304.08485 [cs.CV].
  17. ↑ Zhang, Hang; Li, Xin; Bing, Lidong (2023-06-01). "Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding". arXiv: 2306.02858 [cs.CL].
  18. ↑ OpenAI (2023-03-27). "GPT-4 Technical Report". arXiv: 2303.08774 [cs.CL].
  19. ↑ OpenAI (September 25, 2023). "GPT-4V(ision) System Card" (PDF).
  20. ↑ Pichai, Sundar, Google Keynote (Google I/O '23), timestamp 15:31, retrieved 2023-07-02
  21. ↑ Dey, Victor (2021-09-03). "Beginners Guide to Boltzmann Machine". Analytics India Magazine. Retrieved 2024-03-02.
  22. ↑ "Multimodal Learning with Deep Boltzmann Machine" (PDF). 2014. Archived (PDF) from the original on 2015-06-21. Retrieved 2015-06-14.
  23. ↑ Quach, Katyanna. "Harvard boffins build multimodal AI system to predict cancer". The Register. Archived from the original on 20 September 2022. Retrieved 16 September 2022.
  24. ↑ Chen, Richard J.; Lu, Ming Y.; Williamson, Drew F. K.; Chen, Tiffany Y.; Lipkova, Jana; Noor, Zahra; Shaban, Muhammad; Shady, Maha; Williams, Mane; Joo, Bumjin; Mahmood, Faisal (8 August 2022). "Pan-cancer integrative histology-genomic analysis via multimodal deep learning". Cancer Cell. 40 (8): 865–878.e6. doi: 10.1016/j.ccell.2022.07.004 . ISSN   1535-6108. PMC   10397370 . PMID   35944502. S2CID   251456162.


This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.