Generative Modeling

AI content

CellStrat > Research/Blog > Artificial Intelligence > Generative Modeling

Aug

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars Recently, our AI Lab Researcher Gouthaman Asokan presented an amazing session on Generative Models for Graphs. This is part of our webinar series on Graphs and Graph Neural Networks. Graph is a nonlinear data structure consisting of nodes and edges. Widely used in applications like Physical system interactions, Knowledge graphs, Molecular interactions, Transportation […]

Posted in: Generative Modeling, Graph Neural Networks, Pharma,

Tags: bernoulli distribution, categorical distribution, deep generative model for graph, DGMG, generative model, generative modelling, GrammarVAE, graph embedding, graph grammar, graph neural network, graph propagation, molecular generation, Simplified Molecular Input Line Entry System, SMILES, synthentic graph, synthetic graph, teacher forcing,

Feb

Photo-Realistic Single Image Super-Resolution using SRGAN

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars #AlwaysUpskilling Last Saturday (15th Feb 2020) our AI Lab Team Lead Abdul Azeez presented a superb hands-on workshop on Super-Resolution GANs or SRGANs as they are called. SRGANs are very useful to increase the resolution in images (or create super-resolved images). Basic GAN :- GANs or Generative Adversarial Networks are generative models […]

Posted in: Computer Vision, Deep Learning, Generative Modeling,

Tags: Adversarial Loss, Content Loss, ESPCN, GAN, generative modelling, Generator Loss, Perceptual Loss, Pixel shuffle, PSNR, Single Image Super Resolution, SISR, SRCNN, SRGAN, SSIM, Super Resolution GAN, VDSR,

Feb

3D Printed Textiles and Shoes for the Fashion Industry

Studio Bitonti has developed 3D algorithmic design software called Genysis. The system has been used to create 3D printed replacement hips and cranial implants for the health industry, as well as textiles and shoes for the fashion industry. Genysis does not simply manipulate shapes, it creat-es Stochasitic Lattice structures that can alter the pliability and […]

Posted in: Artificial Intelligence, Deep Learning, Generative Modeling,

Tags: 3D Printing, algorithms, Fashion, Python,

Dec

Generative Modelling with wGAN (Wasserstein GAN)

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars Last Saturday, our AI Lab team Lead Abdul Azeez presented an extensive hands-on workshop on wGANs or Wasserstein GANs. Overview of wGANs :- A GAN is a pair of neural networks – Generator and Discriminator. The G tries to produce real-like images and D tries to distinguish the generated images from real […]

Posted in: Computer Vision, Deep Learning, Generative Modeling,

Tags: 1-Lipschitz function, Earth-Mover Distance, EM Distance, GAN, generative adversarial network, generative modelling, gradient penalty, Jensen-Shannon divergence, JS Divergence, KL Divergence, Kullback-Leibler divergence, Wasserstein distance, Wasserstein GAN, wGAN, wGAN-GP, wGANs,

Dec

Meeting Minutes from CellStrat AI Lab meetup on Saturday 7th Dec 2019 at Bengaluru

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars Minutes from Saturday 7th Dec AI Lab meetup at BLR :- Last Saturday we had fabulous presentations by AI Lab members in BLR. Recommender Systems :- In our Hebbal AI Lab, the day started with a deep session on Recommender Systems by Gurumoorthy Loganathan. Recommender system is a subclass of information filtering […]

Posted in: Computer Vision, Deep Learning, Generative Modeling, Machine Learning, Natural Language Processing, Reinforcement Learning,

Tags: BERT, CycleGAN, GANs, generative modelling, keypoint detection, openpose, optimal policy, product recommendations, Question-Answer Model, recommender systems, reinforcement learning, SQuaD, Wasserstein GAN,

Oct

Meeting Minutes from AI Lab session on Saturday 26th Oct in Bengaluru

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars Last Saturday we had another fantastic set of AI presentations at our AI Lab meetup. Face Recognition System with MTCNN :- First, Jani Basha presented a fabulous model on face recognition system, which involved detecting and recognizing faces from images and videos. One can also use this model to identify humans from […]

Posted in: Computer Vision, Cyber Security, Deep Learning, Generative Modeling, Machine Learning, Security,

Tags: AI, AI lab, artificial intelligence, Computer Vision, deep learning, Deepfake, Disrupt4.0, DL, Face Recognition, Face2face, Fake Video Detection, forged videos, machine learning, Mesoscopic, ML, monte carlo, MTCNN, MTCNN face detector, roulette, stock price prediction, video analytics,

Sep

Meeting Minutes from AI Lab session on Saturday 21st Sep in Bengaluru

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars We had fantastic presentations on advanced Deep Learning concepts at the last Saturday AI Lab. Reinforcement Learning (RL) with Dynamic Programming : First Shubha M. started with a superb session on RL with Dynamic Programming. Dynamic Programming is a concept of breaking a problem into subproblems, solving them and then combining the […]

Posted in: Computer Vision, Deep Learning, Generative Modeling, Reinforcement Learning,

Tags: artificial intelligence, autoencoders, Computer Vision, denoising autoencoders, greedy policy, markov decision processes, object detection, policy improvement, single shot detector, sparse autoencoders, Unsupervised learning, VAE, value iteration,