Preferences...
DescendantsActive learningBayesian classificationNaive Bayes classifierConcept Bottleneck ModelsConditional random fieldsConfusion matrixContinual LearningIncremental Few-shot Text ClassificationNeurala: Lifelong-DNNContrastive LearningContrastive Self-Supervised LearningInfoNCE lossCo-trainingCross-validationData AugmentationBacktranslationSynthetic data (NLP)Automatically Annotated DataSynthetic QA dataGPL (Generative Pseudo Labeling)Dataset DistillationDecision tree learningDeep LearningAI black boxBlackbox NLPLIMEAlphagoAttention mechanismAttention in GraphsAttention + Knowledge GraphsGraph TransformersGraph Attention NetworksSelf-AttentionTransformersAlternative to TransformersSuccesor to TransformersAttention mechanismBERTALBERTBERT + KBBERT + Sentence EmbeddingsSentence-BERTsBERT fine-tuningSentence-BERT: Domain adaptationGPL (Generative Pseudo Labeling)sBERT fine-tuningSentenceBERT and WordsBERT-based entity linkingBERT fine-tuningBERT fine-tuning: instabilitiesBertologyBERTopicCamemBERTDistilBERTDomain-Specific BERTKeyBERTKnowBertGraph Transformershuggingface / transformerskNN-TransformersMixture of ExpertsOpenAI GPTChatGPTChatGPT: competitorsChatGPT: costsChatGPT: programmingChatGPT: ToolsChatGPT pluginsChatGPT Retrieval PluginGPT Code InterpreterChatGPT: trainingChatGPT: use-caseChatGPT+SearchBing+ChatGPTChatGPT Retrieval PluginKnowledge (Raphaël)paper-QAperplexity.aiChatGPT APIChatGPT fine-tuningChatGPT Over Your DataChatGPT pluginsGPT: alternativesGPT: appsGPT/LLM devGPT-2GPT-3GPT-3.5GPT-4GPTsGPT sample codeGPT use-caseChatGPT: use-caseGPT and educationOpenAI: Function callingOpenAI Embeddingsperplexity.aiWindows CopilotReformerSparse TransformersT5 (Text-To-Text Transfer Transformer)Transformer-Based Entity LinkingTransformer based KG embeddingsTransformers: improvementsTransformers: Quadratic complexityTransformers: trainingTransformers explainedSeq2Seq with AttentionBrain vs Deep LearningBackpropagation vs BiologyCatastrophic forgettingCoursera: Deep LearningDebug Deep LearningDeep latent variable modelsDeep learning: implementingDeep Learning: Optimization methodsDeep Learning BookDeep Learning frameworksKerasKeras embedding layerKeras Functional APIPyTorchTensorFlowTensor2TensorTensorFlow 2.0Deep NLPELMoExplainable NLPPre-Trained Language ModelsBERTELMoERNIELLMBardChatGPTChichillaDo LLMs understand?Emergence in LLMsFrugal LLMsFunction Calling (LLM)GeminiGenerative Transformer LMOpenAI GPTPrompting/In-context learningIn-context learningLLMs: extended context windowMany-Shot In-Context LearningLLM Fine-tuning vs promptingPrompt engineeringRetrieval-augmented in-context learningGPT/LLM devGPT-3Hallucination problemInstruction tuningLLaMALLM + CodeLLM + IRHyDERAG (Retrieval-Augmented Generation)HyDELLM Fine-tuning vs RAGRAG: AgentsRAG: chunkingRAG + KGRAG evaluationRAG isn't easyWalkingRAGLLM + KGLLM + structured dataChat over structured dataLLM+SQLLLM CompositionLLM pre-trainingLLMs + scientific papersLLMs in enterprisesLLMs over your dataChatGPT Over Your DataChat over structured dataChat over your dataChatGPT Over Your DataChat over your PDFsChat over your PDFsGPT4AllLlamaIndexJerry LiuLLM TipsLM: tokenizationOpenAI GPTOpen-source LLMSemantic KernelTool-Augmented LLMsChatGPT pluginsLLMs accessing APIsOpenAI: Function callingToolformerOpenAI GPTPromptsPrompt engineeringPrompting/In-context learningPrompt TuningT5 (Text-To-Text Transfer Transformer)ULMFiTXLNetDeep Unsupervised LearningDL: why does it work?Domain Knowledge + Deep LearningKnowledge Graph + Deep LearningAttention + Knowledge GraphsKG-augmented Language ModelsLanguage Models as Knowledge BasesThèse IRIT-Renault NLP-KBKD-MKBKD-MKB biblioKD-MKB paperKD-MKB relatedfast.aiFast.ai coursenbdev.fast.aiInformation theory AND Deep LearningMemory in deep learningHierarchical Memory NetworksMemory EmbeddingsMemory networksNeural MemoryModular Deep LearningNatural Language Semantic SearchNIPS 2017Sparse modelsUncertainty in Deep LearningDimensionality reductionAutoencoderVariational autoencoder (VAE)Principal component analysisSingular Value DecompositionSpectral clusteringText: dimension reductionText feature extractiont-SNEUMAPEmbeddingsCategory EmbeddingDocument embeddingsDoc2VecDSSM (Deep Semantic Similarity Model)Representation of text + metadataEmbedding evaluationWord embedding: evaluationEmbedding Model Fine-tuningsBERT fine-tuningUnsupervised Sentence Embedding LearningEmbedding QuantizationEmbeddings in Information RetrievalEmbeddings in NLPDocument embeddingsMultilingual embeddingsPhrase embeddingsSense embeddingsSentence EmbeddingsA La Carte EmbeddingDoc2VecDSSM (Deep Semantic Similarity Model)E5Sent2VecSentence embeddings: Domain adaptationSentence TransformersBERT + Sentence EmbeddingsSIF embeddingsUniversal Sentence EncoderUnsupervised Sentence Embedding LearningText EmbeddingsE5Geometry of language embeddingsMTEBOpenAI EmbeddingsRepresentation of text + metadataSentence EmbeddingsTopic embeddingsWord embeddingsA La Carte EmbeddingCross-lingual Word EmbeddingsELMoFastTextGloVeLDA2vecSubword embeddingsTopic Models + Word embeddingUsing word embeddingsWord + Entity embeddingsWikipedia2VecWord2vecDoc2VecWord2vec: howtoWord embedding: evaluationWord Embedding CompositionalitySIF embeddingsWord embeddings: introductionWord embeddings with lexical resourcesEntity embeddingsCategory EmbeddingLUKEPoincaré EmbeddingsStarSpaceText-Aware KG embeddingTransEWord + Entity embeddingsGaussian embeddingGraph EmbeddingsKnowledge Graph EmbeddingsConvolutional Knowledge Graph EmbeddingsDismultEntity type representationHierarchy-Aware KG EmbeddingsKG Embeddings LibraryRDF embeddingsRotatEText, KG and embeddingsText-Aware KG embeddingUsing literal descriptions of entitiesWord + Entity embeddingsText-Aware KG embeddingTransETransformer based KG embeddingsNode EmbeddingsOWL2VecKeras embedding layerKnowledge-driven embeddingsKnowledge Graph EmbeddingsLabel EmbeddingCategory EmbeddingMemory EmbeddingsOpenAI EmbeddingsPhrase embeddingsRDF embeddingsSense embeddingsStarSpaceStructured Data EmbeddingText, KG and embeddingsText EmbeddingsTop2VecTopic embeddingsTree embeddingsEncoder-Decoder architectureEnsemble learningBoostingBootstrap aggregating (Bagging)Random forestStacking (ensemble learning)Feature extractionFeature hashing ("Hashing trick")Feature selectionGenerative modelGradient descentHidden Markov modelHierarchical temporal memoryk-means clusteringk-nearest neighborsLearned Index StructuresLearning to hashLogistic regressionMaxent modelsMaxEnt classifier (Multinomial logistic regression)MaxEnt for NLPMulti-task learningNatural Language SupervisionNegative SamplingNeural networksAutoencoderBackpropagationBackpropagation through time (BPTT)Backpropagation vs BiologyCapsule networksConvolutional neural networkCNN 4 NLPConvolutional Knowledge Graph EmbeddingsGraph Convolutional NetworksDeep LearningFine-tuningChatGPT fine-tuningEmbedding Model Fine-tuningInstruction tuningLM Fine-tuningBERT fine-tuningContinued pre-trainingLLM Fine-tuning vs promptingLLM Fine-tuning vs RAGParameter-efficient fine-tuning (PEFT)Adapter modules (LM finetuning)LoRATask-specific modelssBERT fine-tuningGANGraph neural networksGraph Attention NetworksGraph Convolutional NetworksGraph message passingKnowledge distillationDistilBERTMemory requirements in NNNeural knowledgeNeural machine translationNeural network interpretabilityProbing (ML)Neural SearchBEIRCherche (Raphaël)ColBERTDense Passage RetrievalEmbeddings in Information RetrievalExtractive SearchHaystackHybrid SearchMulti-Vector RetrievalNeural Ranking ModelsPineconeREALMtxtaiVespaWeaviateNeuroevolutionNN: introductionNN 4 NLPNN tipsRecurrent neural networkBackpropagation through time (BPTT)LSTMRNN based Language ModelRestricted Boltzmann machineSelf-Organizing MapsSiamese networksSpiking Neural NetworkTwo-Tower neural networkWhat's encoded by a NNPretrained modelsUnsupervised deep pre-trainingPre-Trained Language ModelsProbing (ML)Random forestReinforcement learningMeta Reinforcement LearningRL from Human FeedbackSemi-supervised learningCo-trainingGraph-based Semi-Supervised LearningStochastic gradient descentTarget encodingTensorTransductive LearningVariational Bayesian methodsWeak supervision