Collaborating Authors

pre-trained model

How does Transfer Learning work?


The simple idea of transfer learning is, After Neural Network learned from one task, apply that knowledge to another related task. It is a powerful idea in Deep Learning. You all know in Computer vision and Natural Language Processing tasks required high computational costs and time. So, we can simplify those tasks using Transfer Learning. For example, after we trained a model using images to classify Cars, then that model we can use to recognize other vehicles like trucks.

CNN based Dog Breed Classifier Using Stacked Pretrained Models


In this article, we will learn how to classify images based on fine details of images using a stacked pre-trained model to get maximum accuracy in TensorFlow. Hey folks, I hope you have done some image classification using pre-trained TensorFlow or TensorFlowor other CNN pre-trained models and might have some idea about how we classify images, but when it comes to classifying finely detailed objects (dog breed, cat breed, leaves diseases) this method doesn't give us a good result, in this case, we would prefer model stacking to capture most of the details. Let's get straight to the technicalities of it. In our dataset, we have 120 dog breeds and we will have to classify them using a stacked pre-trained model (TensorFlow, Densenet121) which is trained on Imagenet. We will stack bottleneck features extracted by these models for greater accuracy that will depend on the models we are stacking together. When you work on a classification problem you tend to use a classifier that majorly focuses on the max pooled features that mean it does take fine or small objects into account while training.

Going deeper into Deep Learning


I'd love the thank my friends who gave me permission to use their handsome faces in the name of artificial intelligence science! We can definitely tell that this fine gentleman has brown eyes. On the other hand, the model is pretty certain that this individual has blue eyes with a probability greater than 90%. We have a correct prediction but a not very confident probability of 69% (and that's no coincidence). Finally, we try it on me… not so handsome and no so great prediction confidence.

Hot dog or Not Hot dog


Have you watched the "Silicon Valley" comedy series of HBO? If so, I bet you remember the Not Hotdog app that Jian Yang developed. Here is a clip to refresh your memory. So basically this app identifies whether something is Hot dog or not. Well, we can train with other types of objects to identify them as well.

Fine-tune and host Hugging Face BERT models on Amazon SageMaker


The last few years have seen the rise of transformer deep learning architectures to build natural language processing (NLP) model families. The adaptations of the transformer architecture in models such as BERT, RoBERTa, T5, GPT-2, and DistilBERT outperform previous NLP models on a wide range of tasks, such as text classification, question answering, summarization, and text generation. These models are exponentially growing larger in size from several million parameters to several hundred billion parameters. As the number of model parameters increases, so does the computational infrastructure that is necessary to train these models. This requires a significant amount of time, skill, and compute resources to train and optimize the models.

What is Transfer Learning? -- Idiot Developer


Transfer Learning is a technique in machine learning where we reuse a pre-trained model to solve a different but related problem. It is one of the popular methods to train the deep neural network. It is generally used for image classification tasks where the amount of the dataset is small. In this article, we will go through what transfer learning is, how it works and the advantages it offers. Additionally, we will also cover the most common problems related to it.

PyTorch Ignite -- Classifying Tiny ImageNet with EfficientNet


This includes popular architectures such as ResNet-18, VGG16, GoogLeNet and ResNeXt-50. We will do something different for this project by selecting a pre-trained model that is not within the default list of Torchvision models. In particular, we will be using EfficientNet. EfficientNet is a convolutional neural network architecture and scaling method developed by Google in 2019. It has been shown to surpass state-of-the-art accuracy with up to 10 times better efficiency (i.e.

Offensive Language and Hate Speech Detection with Deep Learning and Transfer Learning Artificial Intelligence

Toxic online speech has become a crucial problem nowadays due to an exponential increase in the use of internet by people from different cultures and educational backgrounds. Differentiating if a text message belongs to hate speech and offensive language is a key challenge in automatic detection of toxic text content. In this paper, we propose an approach to automatically classify tweets into three classes: Hate, offensive and Neither. Using public tweet data set, we first perform experiments to build BI-LSTM models from empty embedding and then we also try the same neural network architecture with pre-trained Glove embedding. Next, we introduce a transfer learning approach for hate speech detection using an existing pre-trained language model BERT (Bidirectional Encoder Representations from Transformers), DistilBert (Distilled version of BERT) and GPT-2 (Generative Pre-Training). We perform hyper parameters tuning analysis of our best model (BI-LSTM) considering different neural network architectures, learn-ratings and normalization methods etc. After tuning the model and with the best combination of parameters, we achieve over 92 percent accuracy upon evaluating it on test data. We also create a class module which contains main functionality including text classification, sentiment checking and text data augmentation. This model could serve as an intermediate module between user and Twitter.

Improving Similar Language Translation With Transfer Learning Artificial Intelligence

We investigate transfer learning based on pre-trained neural machine translation models to translate between (low-resource) similar languages. This work is part of our contribution to the WMT 2021 Similar Languages Translation Shared Task where we submitted models for different language pairs, including French-Bambara, Spanish-Catalan, and Spanish-Portuguese in both directions. Our models for Catalan-Spanish ($82.79$ BLEU) and Portuguese-Spanish ($87.11$ BLEU) rank top 1 in the official shared task evaluation, and we are the only team to submit models for the French-Bambara pairs.

Wu Dao 2.0: Why China is Leading the Artificial Intelligence Race?


Wu Dao 2.0 has surpassed OpenAI's GPT-3 in so many ways. China could grow to monopolise the language modelling world. Artificial intelligence models have become a strong informal indicator of national and continental progress. Wu Dao 2.0 means enlightenment. It is dubbed as China's first homegrown super-scale intelligent model system, and was led by BAAI Research Academic Vice President and Tsinghua University Professor Tang Jie.