## Digica # Blog ### Discover more of what matters to you - [Artificial intelligence](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=15:artificial-intelligence) - [Machine learning](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=7:machine-learning) - [technology](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=21:technology) - [computer vision](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=33:computer-vision) - [Deep learning](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=14:deep-learning) - [Data Science](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=8:data-science) - [trends](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=18:trends) - [neural network](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=47:neural-network) - [Data Models](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=9:data-models) - [LLM](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=86:llm) - [future](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=22:future) - [attention mechanism](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=24:attention-mechanism) - [Open CV](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=5:open-cv) - [autonomous driving](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=73:autonomous-driving) - [Object detection](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=6:object-detection) - [LiDAR](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=75:lidar) - [synthetic data](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=52:synthetic-data) - [industry4.0](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=53:industry4-0) - [dooms day](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=23:dooms-day) - [Evaluation](https://www.digica.com/index.php?option=com_tags&view=tag&id%5B0%5D=31:evaluation) [ ![](https://www.digica.com/templates/yootheme/cache/7e/robot-g58c157ef1_1920-7e445f8d.jpeg) ### From the diary of a Data Scientist Data is all around us, and we don't even see it. Data Scientists usually work on projects related to well known topics in Data Science and Machine Learning, for example, projects that rely on Computer Vision, Natural La… Sylwana Kaźmierska 06.27.2022 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=177:from-the-diary-of-a-data-scientist&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=177:from-the-diary-of-a-data-scientist&catid=27) [ ![A handful of thoughts on the practical use of Generative Adversarial Networks (GANs)](https://www.digica.com/templates/yootheme/cache/3d/images_Artificial-Intelligence_computer-vision_catscan-3df5dfe5.png) ### A handful of thoughts on the practical use of Generative Adversarial Networks (GANs) What are Generative Adversarial Networks? A Generative Adversarial Network (GAN) is a concept that was developed in 2014 by a team of distinguished researchers led by Ian J. Goodfellow. In short, we train two deep neura… Adam Gurgul 05.30.2022 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=176:a-handful-of-thoughts-on-the-practical-use-of-generative-adversarial-networks-gans&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=176:a-handful-of-thoughts-on-the-practical-use-of-generative-adversarial-networks-gans&catid=27) [ ![](https://www.digica.com/templates/yootheme/cache/92/Vision_methods-92e27f92.jpeg) ### Context is (nearly) everything - how humans and AI understand visual stimuli differently. Or, when is a bird a bird? As humans, we have a visual system that allows us to see (extract and understand) shapes, colours and contours. So why do we see every image as a different image? How do we know, for example, that a box in an image is, in realit… Adam Szummer 04.26.2022 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=175:context-is-nearly-everything-how-humans-and-ai-understand-visual-stimuli-differently-or-when-is-a-bird-a-bird-and-when-is-a-plane-a-plane&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=175:context-is-nearly-everything-how-humans-and-ai-understand-visual-stimuli-differently-or-when-is-a-bird-a-bird-and-when-is-a-plane-a-plane&catid=27) [ ![Will robots ever make music?](https://www.digica.com/templates/yootheme/cache/21/cobain_free_licence_black_and_white-21e7738f.png) ### Will robots ever make music? Piotr Czembrowski 03.22.2022 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=174:will-robots-ever-make-music&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=174:will-robots-ever-make-music&catid=27) [ ![](https://www.digica.com/templates/yootheme/cache/7c/catscan-7c5b2635.png) ### What I like about autoencoders Autoencoders have existed in Data Science for a long time. This type of model has three sequential parts: the input layer (encoder); the hidden layer; and the output layer (decoder). It seems like a simple concept, but it is very powerf… Joanna Piwko 03.16.2022 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=173:what-i-like-about-autoencoders&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=173:what-i-like-about-autoencoders&catid=27) [ ![](https://www.digica.com/templates/yootheme/cache/88/advanced-domains-88aac139.jpeg) ### How to fool a neural network? Nowadays, no one needs to be convinced of the power and usefulness of deep neural networks. AI solutions based on neural networks have revolutionised almost every area of ​​technology, business, medicine, science and military ap… Mateusz Papierz 02.22.2022 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=171:how-to-fool-a-neural-network&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=171:how-to-fool-a-neural-network&catid=27) [ ![](https://www.digica.com/templates/yootheme/cache/7c/catscan-7c5b2635.png) ### Deep learning models which pay attention (part II) - Attention (special focus) in Computer Vision In the previous article, I described attention mechanisms by using an example of natural language processing. This method was first used in language processing, but this is not its only usage. We can also use attention mechanism… Joanna Piwko 01.31.2022 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=170:deep-learning-models-which-pay-attention-part-ii-attention-special-focus-in-computer-vision&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=170:deep-learning-models-which-pay-attention-part-ii-attention-special-focus-in-computer-vision&catid=27) [ ![](https://www.digica.com/templates/yootheme/cache/b3/heart-b370866d.png) ### How to avoid denial in Data Science For some reason, it is quite natural for people to argue with each other all the time. Wives argue with husbands. Children argue with their parents. Facebook users argue with other Facebook users. United fans argue with City fan… Patryk Seweryn 01.05.2022 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=169:how-to-avoid-denial-in-data-science&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=169:how-to-avoid-denial-in-data-science&catid=27) [ ![](https://www.digica.com/templates/yootheme/cache/16/bot-robots_2-162621f9.jpeg) ### Improving Bot Detection with AI According to some sources, over 40% of all Internet traffic is made up of bot traffic. And we know that malicious bots are a significant proportion of current bot traffic. This article describes a number of strategies (Machine Learning… Sylwana Kaźmierska 12.17.2021 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=168:improving-bot-detection-with-ai&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=168:improving-bot-detection-with-ai&catid=27) [ ![](https://www.digica.com/templates/yootheme/cache/79/AI_deep_learning-796744c7.jpeg) ### Deep learning models which pay attention (part I) The attention mechanism made big changes in deep learning. Thanks to this, models can achieve better results. This mechanism was also the inspiration for perceivers and also transformer neural networks . And transformers… Joanna Piwko 11.24.2021 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=167:deep-learning-models-which-pay-attention-part-i&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=167:deep-learning-models-which-pay-attention-part-i&catid=27) [ ![](https://www.digica.com/templates/yootheme/cache/64/human-ai-balance-6463dca6.jpeg) ### Consequences of AI Some say artificial intelligence (AI) will be the next big thing after the internet: a tool enabling new industries and improving the lives of ordinary people. Others think AI is the greatest threat to society as we know it. This articl… Tigran Soghbatyan 11.16.2021 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=166:consequences-of-ai&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=166:consequences-of-ai&catid=27) [ ![](https://www.digica.com/templates/yootheme/cache/ab/AdobeStock_283707846_2-ab9f4589.jpeg) ### System 2 Deep Learning Review of Yoshua Bengio’s lecture at the Artificial General Intelligence 2021 Conference At the 2021 Artificial General Intelligence Conference, a star keynote speaker was Yoshua Bengio. He has been one of the leading figures of deep l… Martin Kolar 11.04.2021 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=165:system-2-deep-learning&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=165:system-2-deep-learning&catid=27) [ ![](https://www.digica.com/templates/yootheme/cache/c3/waveform1-c3eee673.png) ### Why is explaining machine learning models important? The main focus in machine learning projects is to optimize metrics like accuracy, precision, recall, etc. We put effort into hyper-parameter tuning or designing good data pre-processing. What if these efforts don’t seem to work?&n… Joanna Piwko 10.27.2021 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=164:why-is-explaining-machine-learning-models-important&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=164:why-is-explaining-machine-learning-models-important&catid=27) [ ![Working with models vs. working with data](https://www.digica.com/templates/yootheme/cache/65/Data_Science-hero-65baba1a.jpeg) ### Working with models vs. working with data If I was to point out one most common mistake of a rookie Data Scientist, it’s their focus on the model, not on the data. Lukasz Kuncewicz 10.12.2021 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=159:working-with-models-vs-working-with-data&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=159:working-with-models-vs-working-with-data&catid=27) [ ![](https://www.digica.com/templates/yootheme/cache/1c/Heart_rate_detection_with_Open_CV-1c316a44.jpeg) ### Heart rate detection with Open CV Since it’s 2021, it’s probably no surprise to you that heart rate can be measured using different gadgets like smartphones or smartwatches. Sylwana Kazmierska 09.21.2021 [Read more](https://www.digica.com/index.php?option=com_content&view=article&id=158:heart-rate-detection-with-open-cv&catid=27) ](https://www.digica.com/index.php?option=com_content&view=article&id=158:heart-rate-detection-with-open-cv&catid=27)