Big Data Science

2021-04-08 06:26:41 In January 2021 Open.AI presented the new ML-model, neural network called DALL·E that creates images from text captions for concepts on natural language. It has 12-billion parameters and based on GPT-3. DALL·E was trained to generate images from text descriptions, using a dataset of text–image pairs. It can create anthropomorphized versions of animals and objects, combine unrelated concepts in plausible ways, render texts, and apply transformations to existing images.
Like GPT-3, DALL·E is a transformer language model. It receives both the text and the image as a single stream of data containing up to 1280 tokens, and is trained using maximum likelihood to generate all of the tokens, one after another. A token is any symbol from a discrete vocabulary, e.g. each English letter is a token from a 26-letter alphabet. DALL·E’s vocabulary has tokens for both text and image concepts. Specifically, each image caption is represented using a maximum of 256 BPE-encoded tokens with a vocabulary size of 16384, and the image is represented using 1024 tokens with a vocabulary size of 8192.
The images are preprocessed to 256x256 resolution during training. Similar to VQVAE, each image is compressed to a 32x32 grid of discrete latent codes using a discrete VAE pretrained using a continuous relaxation to obviate the need for an explicit codebook, EMA loss, or dead code revival. Also this trick can scale up to large vocabulary sizes and allows DALL·E to generate an image from scratch and to regenerate any rectangular region of an existing image that extends to the bottom-right corner consistent with the text prompt.
The attention mask at each of its 64 self-attention layers allows each image token to attend to all text tokens. DALL·E uses the standard causal mask for the text tokens, and sparse attention for the image tokens with either a row, column, or convolutional attention pattern, depending on the layer. The embeddings are produced by an encoder pretrained using a contrastive loss, not unlike CLIP.
https://openai.com/blog/dall-e/ Open / Comment

2021-04-05 08:01:51 How AI helps to increase production quality +25% up: Fujitsu experience
Japanese tech giant has developed an AI system highlights abnormalities in the appearance of products to help detect manufacturing issues earlier before materials are wasted.
ML-model trained on simulated images of products with abnormalities is able to detect different issues. For example frayed threads or defective wiring patterns on multicolor carpets or electronics parts with different wiring shapes. The ML-algorithm gained high quality: AUROC score of defects finding is more than 98%. The technology was tested at Fujitsu Plant in Nagano, which manufactures electronic equipment. The results showed a 25% reduction in the man-hours for inspecting printed circuit boards.
https://artificialintelligence-news.com/2021/03/29/fujitsu-develops-ai-product-abnormalities-manufacturing/ Open / Comment

2021-04-03 14:14:56 Deep Learning helps you to be healthy!
For years, physicians have relied on visual inspection to identify suspicious pigmented lesions (SPLs), which can be an indication of skin cancer. Early-stage identification of SPLs can improve melanoma prognosis and significantly reduce treatment cost. But it is not easy quickly find and prioritize SPLs due to the high volume of pigmented lesions. Researchers from MIT have devised a new AI pipeline, using deep convolutional neural networks (DCNNs) and applying them to analyzing SPLs through the wide-field photography common in smartphones.
A wide-field image, acquired with a smartphone camera, shows large skin sections from a patient. An automated system detects, extracts, and analyzes all pigmented skin lesions observable in the wide-field image. A pre-trained DCNN ML-models determines the suspiciousness of individual pigmented lesions and marks them: further inspection as yellow, referral to dermatologist as red. Extracted features are used to further assess pigmented lesions and to display results in a heatmap format.
DCNNs are deep learning algorithms are used to classify images to then cluster them for performing a photo search.
https://news.mit.edu/2021/artificial-intelligence-tool-can-help-detect-melanoma-0402 Open / Comment

2021-03-31 06:28:11 If you do not want to study grammar and history, use ML to pass the exams! GPT-3 has done it with U.S. History, Research Methods, Creative Writing, and Law. In 3-20 minutes, NN was able to mimic human writing in areas of grammar, syntax, and word frequency and get the same feedback as the human writers
https://www.zdnet.com/article/ai-can-write-a-passing-college-paper-in-20-minutes/ Open / Comment

2021-03-29 06:46:01 Looking for interesting reading? Take the TOP-21 books about Data Science, Engineering and Statistics – must to be read in 2021 https://towardsdatascience.com/21-data-science-books-you-should-read-in-2021-db625e97feb6
And short-list of 5 items https://medium.com/curious/5-books-every-data-scientist-should-read-in-2021-206609d8593b Open / Comment

2021-03-27 07:45:33 How to assess the potential effectiveness of medical drugs: new method DeepBAR form MIT researchers to calculate the binding affinities between drug candidates and their targets. It is based on GAN-models for analyzing molecular structures as images
https://news.mit.edu/2021/drug-discovery-binding-affinity-0315 Open / Comment

2021-03-25 06:07:56 Why modern AI for Computer Vision should have Multimodal Neurons and how this Faceted Feature Visualization rises the accuracy of predictions and classifications. New paper from
OpenAI researchers https://distill.pub/2021/multimodal-neurons/ Open / Comment

2021-03-23 05:55:06 Meet the CLIP (Contrastive Language – Image Pre-training) - new Neural Net from OpenAI: it can be instructed in natural language to perform a great variety of classification benchmarks, without directly optimizing for the benchmark’s performance, similar to the “zero-shot” capabilities of GPT-2 and GPT-3. CLIP is based on zero-shot transfer, natural language supervision, and multimodal learning to recognize a wide variety of visual concepts in images and associate them with their names. Read more where you can use this unique ML-model https://openai.com/blog/clip/ Open / Comment

2021-03-21 07:43:00 Not only Deep Learning: new approach to build AI systems working as human brain - sparse coding principle to supply series of local functions in synaptic learning rules and reduce number of adjusting data in NN-model. The startup Nara Logics from MIT alumnus is trying to increase effectiveness of AI by mimicking the brain structure and function at the circuit level.
https://news.mit.edu/2021/nara-logics-ai-0312 Open / Comment

2021-03-19 07:04:12 Deep fake is not too simple: interview with Belgium VFX specialist Chris Ume, creator of viral video about fake Tom Cruise. Why only ML-algorithm is not enough to get high quality result and you need thorough tune video effects manually
https://www.theverge.com/2021/3/5/22314980/tom-cruise-deepfake-tiktok-videos-ai-impersonator-chris-ume-miles-fisher Open / Comment