InfoQ Homepage Deep Learning Content on InfoQ
-
Zero-Copy In-Memory Sharing of Large Distributed Data: V6d
Zero-copy and in-memory data manager Vineyard (v6d) is maintained as a CNCF sandbox project and provides distributed operators that can be utilized to share immutable data within or across cluster nodes. V6d is of interest particularly for deep network training on big (sharded) datasets such as large language and graph models.
-
DeepMind Open-Sources AI Interpretability Research Tool Tracr
Researchers at DeepMind have open-sourced TRAnsformer Compiler for RASP (Tracr), a compiler that translates programs into neural network models. Tracr is intended for research in mechanistic interpretability of Transformer AI models such as GPT-3.
-
Stanford Researchers Develop Brain-Computer Interface for Speech Synthesis
Researchers from Stanford University have developed a brain-computer interface (BCI) for synthesizing speech from signals captured in a patient's brain and processed by a recurrent neural network (RNN). The prototype system can decode speech at 62 words-per-minute, 3.4x faster than previous BCI methods.
-
Carnegie Mellon Researchers Develop AI Model for Human Detection via WiFi
Researchers from the Human Sensing Laboratory at Carnegie Mellon University (CMU) have published a paper on DensePose From WiFi, an AI model which can detect the pose of multiple humans in a room using only the signals from WiFi transmitters. In experiments on real-world data, the algorithm achieves an average precision of 87.2 at the 50% IOU threshold.
-
Unsupervised Object Detection and Semantic Segmentation Using Deep Learning
Meta AI released CutLER, a state-of-the-art zero-shot unsupervised object detector which improves detection performance by over 2.7 times on 11 benchmark datasets for different domains like video frames, painting, sketches, etc. This model’s simplicity allows compatibility with different object-detection architectures across different domains.
-
Microsoft Open Sources AI Prompt Optimization Toolkit LMOps
Microsoft Research open sourced LMOps, a collection of tools for improving text prompts used as input to generative AI models. The toolkit includes Promptist, which optimizes a user's text input for text-to-image generation, and Structured Prompting, a technique for including more examples in a few-shot learning prompt for text generation.
-
DeepMind Announces Minecraft-Playing AI DreamerV3
Researchers from DeepMind and the University of Toronto announced DreamerV3, a reinforcement-learning (RL) algorithm for training AI models for many different domains. Using a single set of hyperparameters, DreamerV3 outperforms other methods on several benchmarks and can train an AI to collect diamonds in Minecraft without human instruction.
-
BigCode Project Releases Permissively Licensed Code Generation AI Model and Dataset
The BigCode Project recently released The Stack, a 6.4TB dataset containing de-duplicated source code from permissively licensed GitHub repositories which can be used to train code generation AI models. BigCode also released SantaCoder, a 1.1B parameter code generation model trained on The Stack. SantaCoder outperforms similar open-source code generation models.
-
3D Point Cloud Object from Text Prompts Using Diffusion Models
OpenAI recently released an alternative method called Point-E for 3D object generation from text prompts that takes less than two minutes on a single GPU, versus the other methods that could take a few GPU hours. This new model is based on diffusion models, which are generative models like GLIDE and StableDiffusion.
-
Google AI Unveils Muse, a New Text-to-Image Transformer Model
Google AI released a research paper about Muse, a new Text-To-Image Generation via Masked Generative Transformers that can produce photos of a high quality comparable to those produced by rival models like the DALL-E 2 and Imagen at a rate that is far faster.
-
Deep Learning Pioneer Geoffrey Hinton Publishes New Deep Learning Algorithm
Geoffrey Hinton, professor at the University of Toronto and engineering fellow at Google Brain, recently published a paper on the Forward-Forward algorithm (FF), a technique for training neural networks that uses two forward passes of data through the network, instead of backpropagation, to update the model weights.
-
PyTorch-Nightly Struck by Supply Chain Attack Exfiltrating Data and Files
Developers who installed the nightly builds of PyTorch between December 25 and December 30, 2022, are recommended to uninstall it and purge their pip cache to get rid of a malicious package, say PyTorch maintainers. The new attack highlights a recent trend.
-
Amazon Releases Fortuna, an Open-Source Library for ML Model Uncertainty Quantification
AWS announced that Fortuna, an open-source toolkit for ML model uncertainty quantification, has been made generally available. Any trained neural network can be used with the calibration methods offered by Fortuna, such as conformal prediction, to produce calibrated uncertainty estimates.
-
Google Publishes Technique for AI Language Model Self-Improvement
Researchers at Google and University of Illinois at Urbana-Champaign (UIUC) have published a technique called Language Model Self-Improved (LMSI), which fine-tunes a large language model (LLM) on a dataset generated by that same model. Using LMSI, the researchers improved the performance of the LLM on six benchmarks and set new state-of-the-art accuracy records on four of them.
-
Researchers Publish Survey of Algorithmically-Efficient Deep Learning
Researchers from Lawrence Livermore National Laboratory and MosaicML have published a survey of over 200 papers on algorithmically-efficient deep learning. The survey includes a taxonomy of methods to speed up training as well as a practitioner's guide for mitigating training bottlenecks.